TY - CPAPER TI - Leben in Deutschland : An Intelligent Tutoring Game for the German Citizenship Test AU - Haase, Felix AU - Tanirak, Kemal AU - Langer, Johannes AU - Miroliaei, Shamim AU - Mehlich, Jochen AU - Schmid, Ute PY - 2026 T2 - The Proceedings of the 20th European Conference on Games Based Learning VL - 20 IS - 1 SP - 327-336 PB - Academic Conferences International Limited CY - Reading, UK SN - 2049-100X DO - 10.34190/ecgbl.20.1.5467 UR - https://fis.uni-bamberg.de/handle/uniba/117562 LA - eng ER - TY - CPAPER TI - Human-AI Collaboration in Coding : A Trust Perspective AU - Niemann, Sonja AU - Schmid, Ute PY - 2026 SP - 1-13 PB - Otto-Friedrich-Universität CY - Bamberg SN - 1863-2122 UR - https://fis.uni-bamberg.de/handle/uniba/117281 LA - eng AB - Generative AI (GenAI) is transforming software development and Computer Science (CS) education, raising critical questions about trust in human-AI collaboration. This paper examines trust in GenAI from interdisciplinary perspectives, assessing existing trust frameworks and their applicability. Seemingly contradictory definitions and approaches are discussed and a solution is presented that could resolve the contradictions. We explore how trust affects adoption in education and software development, reviewing measurement approaches and implications for calibrated trust. Our findings highlight the gap between theoretical trust and practical reliance, contributing to the discourse on AI usability and integration. KW - Generative AI KW - Trust KW - Trustworthy KW - Human-AI Collaboration ER - TY - JOUR TI - Kompetenzen für eine datenbewusste Gesellschaft AU - Weiss, Eva-Maria AU - Gärtig-Daugs, Anja AU - Schmid, Ute Maria PY - 2026 JO - On : Lernen in der digitalen Welt IS - 26, Daten teilen und schützen SP - 27-29 PB - Friedrich Verlag CY - Hannover SN - 2700-1091 UR - https://fis.uni-bamberg.de/handle/uniba/117252 LA - deu ER - TY - JOUR TI - Data Literacy in der Grundschule AU - Weiss, Eva-Maria AU - Gärtig-Daugs, Anja AU - Schmid, Ute PY - 2026 JO - Schule leiten IS - 45, Nachhaltige Schulentwicklung – Ans EINGEMACHTE gehen SP - 38-39 PB - Friedrich-Verlag CY - Hannover SN - 2365-2195 UR - https://fis.uni-bamberg.de/handle/uniba/117253 LA - deu ER - TY - JOUR TI - Was alle über Künstliche Intelligenz wissen sollen und wie KI-bezogene Kompetenzen in der Schule entwickelt werden können : Weiterführende Überlegungen zum GI-Positionspapier „Künstliche Intelligenz in der Bildung“ AU - Losch, Daniel AU - Jaschke, Steffen AU - Michaeli, Tilman AU - Opel, Simone AU - Schmid, Ute AU - Seegerer, Stefan AU - Stechert, Peer PY - 2026 SP - 38–46 PB - Otto-Friedrich-Universität CY - Bamberg UR - https://fis.uni-bamberg.de/handle/uniba/116651 LA - deu AB - Aufbauend auf dem Positionspapier der Gesellschaft für Informatik zur Bedeutung von Künstlicher Intelligenz (KI) in der Bildung wird im Beitrag die Notwendigkeit diskutiert, Schüler*innen sowie Lehrkräfte auf die Chancen und Herausforderungen von KI vorzubereiten. Es werden verschiedene Ansätze zum Lehren und Lernen über und mit KI vorgestellt, darunter die Integration von KI in den Informatikunterricht, die Verwendung von Unplugged-Ansätzen und die Entwicklung von KI-bezogenen Kompetenzen in der berufichen Bildung. Der Beitrag betont die Bedeutung von Informatik als Pfichtfach im allgemeinbildenden Unterricht. Abschließend werden die Konsequenzen von KI für die Bildung und die Notwendigkeit eines interdisziplinären Diskurses über die Gestaltung von Bildung in einer digital geprägten Welt diskutiert. KW - - ER - TY - BOOK TI - Handbuch der Künstlichen Intelligenz ED - Braun, Tanya ED - Hüllermeier, Eyke ED - Schmid, Ute Maria ED - Görz, Günther PY - 2026 PB - De Gruyter Oldenbourg CY - Berlin/München/Boston ET - 7 SN - 978-3-11-138669-0 DO - 10.1515/9783111386690 UR - https://fis.uni-bamberg.de/handle/uniba/116050 LA - deu ER - TY - RPRT TI - Projekt MINT-LinK : Motive zur Teilnahme an und Zugangswege zu den Angeboten des MINT-Zentrums Hirschaid AU - Heder, Kim AU - Weiss, Eva-Maria AU - Bircan, Berat AU - Yu, Mengmeng AU - Schmid, Ute AU - Wolter, Ilka PY - 2026 PB - Otto-Friedrich-Universität CY - Bamberg UR - https://fis.uni-bamberg.de/handle/uniba/115720 LA - deu AB - Das Verbundprojekt MINT-LinK begleitet den Aufbau des MINT-Bildungszentrums in Hirschaid mit dem Ziel, fundierte wissenschaftliche Handlungsimplikationen zu entwickeln. Das Projekt umfasst die wissenschaftliche Begleitung der initialen Aufbauphase des MINT-Zentrums sowie Forschungsanalysen zu den Voraussetzungen der Beteiligung Jugendlicher an MINT-Lernangeboten und den Erfolgsfaktoren außerschulischer non-formaler Lernkontexte. Zusätzlich werden Lernangebote mit dem Schwerpunkt auf Künstlicher Intelligenz konzipiert. Finanziert wird das Projekt vom Bundesministerium für Bildung, Familie, Senioren, Frauen und Jugend (BMBFSFJ, vormals BMBF). KW - MINT KW - wissenschaftliche Begleitung KW - Bildungsforschung KW - non-formal ER - TY - RPRT TI - Projekt MINT-LinK : Motive zur Teilnahme an und Zugangswege zu den Angeboten des MINT-Zentrums Hirschaid AU - Heder, Kim AU - Weiss, Eva-Maria AU - Bircan, Berat AU - Yu, Mengmeng AU - Schmid, Ute AU - Wolter, Ilka PY - 2026 DO - 10.5157/MINT-LinK:Bericht:01 UR - https://fis.uni-bamberg.de/handle/uniba/115725 LA - deu AB - Das Verbundprojekt MINT-LinK begleitet den Aufbau des MINT-Bildungszentrums in Hirschaid mit dem Ziel, fundierte wissenschaftliche Handlungsimplikationen zu entwickeln. Das Projekt umfasst die wissenschaftliche Begleitung der initialen Aufbauphase des MINT-Zentrums sowie Forschungsanalysen zu den Voraussetzungen der Beteiligung Jugendlicher an MINT-Lernangeboten und den Erfolgsfaktoren außerschulischer non-formaler Lernkontexte. Zusätzlich werden Lernangebote mit dem Schwerpunkt auf Künstlicher Intelligenz konzipiert. Finanziert wird das Projekt vom Bundesministerium für Bildung, Familie, Senioren, Frauen und Jugend (BMBFSFJ, vormals BMBF). KW - MINT KW - wissenschaftliche Begleitung KW - Bildungsforschung KW - non-formal ER - TY - JOUR TI - The SME AI Experience Center : Overcoming AI Adoption Barriers for SMEs in Industrial Production AU - Knoblach, Judith AU - Vogl, Lena AU - Wehnert, Camilla AU - Carbon, Claus-Christian AU - Franz, Julia AU - Schmid, Ute PY - 2026 SP - 99-104 PB - Otto-Friedrich-Universität CY - Bamberg UR - https://fis.uni-bamberg.de/handle/uniba/115655 LA - eng AB - The development of tools based on Artificial Intelligence (AI) provides significant potential to enhance industrial production, but many small and medium-sized enterprises (SMEs) in more rural areas, such as the study area Upper Franconia in Germany, encounter difficulties in implementing them due to limited resources and expertise. The SME AI Experience Center at the Cleantech Innovation Park offers practical support for AI integration through interactive workshops and a production plant simulating manufacturing processes. It showcases possibilities for the digital transformation by using different types of sensors and the potential of applying machine learning for tasks such as intelligent supply chains, predictive maintenance and quality control. The particular focus is on AI for sustainability. Furthermore, SME managers and workers will be aware that most AI technologies do not result in fully autonomous systems that replace the human workforce but that AI tools often rely on human-AI collaboration. KW - SME KW - Experience of AI KW - AI in manufacturing KW - AI training KW - AI adoption ER - TY - JOUR TI - The SME AI Experience Center : Overcoming AI Adoption Barriers for SMEs in Industrial Production AU - Knoblach, Judith AU - Vogl, Lena AU - Wehnert, Camilla AU - Carbon, Claus-Christian AU - Franz, Julia AU - Schmid, Ute PY - 2026 JO - Künstliche Intelligenz : KI : German journal of artificial intelligence VL - 40 IS - 1 SP - 99-104 PB - Springer CY - Berlin SN - 1610-1987 DO - 10.1007/s13218-025-00899-4 UR - https://fis.uni-bamberg.de/handle/uniba/115654 LA - eng AB - The development of tools based on Artificial Intelligence (AI) provides significant potential to enhance industrial production, but many small and medium-sized enterprises (SMEs) in more rural areas, such as the study area Upper Franconia in Germany, encounter difficulties in implementing them due to limited resources and expertise. The SME AI Experience Center at the Cleantech Innovation Park offers practical support for AI integration through interactive workshops and a production plant simulating manufacturing processes. It showcases possibilities for the digital transformation by using different types of sensors and the potential of applying machine learning for tasks such as intelligent supply chains, predictive maintenance and quality control. The particular focus is on AI for sustainability. Furthermore, SME managers and workers will be aware that most AI technologies do not result in fully autonomous systems that replace the human workforce but that AI tools often rely on human-AI collaboration. KW - SME KW - Experience of AI KW - AI in manufacturing KW - AI training KW - AI adoption ER - TY - JOUR TI - From Latent to Lucid : Transforming Knowledge Graph Embeddings into Interpretable Structures with KGEPrisma AU - Wehner, Christoph AU - Iliopoulou, Chrysa AU - Schmid, Ute AU - Besold, Tarek R. PY - 2026 SP - 1-31 PB - Otto-Friedrich-Universität CY - Bamberg UR - https://fis.uni-bamberg.de/handle/uniba/115362 LA - eng AB - In this paper, we introduce a post-hoc and local explainable AI method tailored for Knowledge Graph Embedding (KGE) models. These models are essential to Knowledge Graph Completion yet criticized for their black-box nature. Despite their success in capturing the semantics of knowledge graphs through high-dimensional latent representations, their inherent complexity poses substantial challenges to explainability. While existing methods like Kelpie use resource-intensive perturbation to explain KGE models, our approach directly decodes the latent representations encoded by KGE models, leveraging the smoothness of the embeddings, which follows the principle that similar embeddings reflect similar behaviours within the Knowledge Graph, meaning that nodes are similarly embedded because their graph neighbourhood looks similar. This principle is commonly referred to as smoothness. By identifying symbolic structures, in the form of triples, within the subgraph neighborhoods of similarly embedded entities, our method identifies the statistical regularities on which the models rely and translates these insights into human-understandable symbolic rules and facts. This bridges the gap between the abstract representations of KGE models and their predictive outputs, providing clear and interpretable insights. The contributions include a novel post-hoc and local explainable AI method for KGE models, which provides immediate and faithful explanations without retraining, thereby facilitating real-time application on large-scale knowledge graphs. The method’s flexibility enables the generation of rule-based, instance-based, and analogy-based explanations, meeting diverse user needs. Extensive evaluations show the effectiveness of our approach in delivering faithful and well-localized explanations, enhancing the transparency and trustworthiness of KGE models. KW - Knowledge graphs KW - Knowledge graph embedding KW - Explainability KW - XAI KW - Interpretability ER - TY - JOUR TI - From Latent to Lucid : Transforming Knowledge Graph Embeddings into Interpretable Structures with KGEPrisma AU - Wehner, Christoph AU - Iliopoulou, Chrysa AU - Schmid, Ute AU - Besold, Tarek R. PY - 2026 JO - Machine Learning VL - 115 IS - 6, 136 SP - 1-31 PB - Springer Science + Business Media B.V CY - Dordrecht [u.a.] SN - 1573-0565 DO - 10.1007/s10994-026-07052-8 UR - https://fis.uni-bamberg.de/handle/uniba/115270 LA - eng AB - In this paper, we introduce a post-hoc and local explainable AI method tailored for Knowledge Graph Embedding (KGE) models. These models are essential to Knowledge Graph Completion yet criticized for their black-box nature. Despite their success in capturing the semantics of knowledge graphs through high-dimensional latent representations, their inherent complexity poses substantial challenges to explainability. While existing methods like Kelpie use resource-intensive perturbation to explain KGE models, our approach directly decodes the latent representations encoded by KGE models, leveraging the smoothness of the embeddings, which follows the principle that similar embeddings reflect similar behaviours within the Knowledge Graph, meaning that nodes are similarly embedded because their graph neighbourhood looks similar. This principle is commonly referred to as smoothness. By identifying symbolic structures, in the form of triples, within the subgraph neighborhoods of similarly embedded entities, our method identifies the statistical regularities on which the models rely and translates these insights into human-understandable symbolic rules and facts. This bridges the gap between the abstract representations of KGE models and their predictive outputs, providing clear and interpretable insights. The contributions include a novel post-hoc and local explainable AI method for KGE models, which provides immediate and faithful explanations without retraining, thereby facilitating real-time application on large-scale knowledge graphs. The method’s flexibility enables the generation of rule-based, instance-based, and analogy-based explanations, meeting diverse user needs. Extensive evaluations show the effectiveness of our approach in delivering faithful and well-localized explanations, enhancing the transparency and trustworthiness of KGE models. KW - Knowledge graphs KW - Knowledge graph embedding KW - Explainability KW - XAI KW - Interpretability ER - TY - CPAPER TI - Comparing Mask R-CNN and Mask2Former architectures for individual tree crown delineation AU - Ruschhaupt, Sonja AU - Troles, Jonas AU - Schmid, Ute Maria PY - 2026 SP - 167-178 PB - Otto-Friedrich-Universität CY - Bamberg UR - https://fis.uni-bamberg.de/handle/uniba/115221 LA - eng AB - Weather anomalies caused by the anthropogenic climate crisis challenge environmental workers such as foresters with an increasing number of responsibilities. In addition to providing attractive conditions for new generations of workers, deep-learning tools can ease processes for better efficiency. Tree instance segmentation has potential for many functionalities that support arborists and foresters by detecting and classifying singular trees. In the past, Mask R-CNN was primarily applied due to its outstanding performance on the 2016 COCO dataset challenge. As an alternative, we suggest Mask2Former, which outperforms Mask R-CNN on the COCO dataset. Additionally, we test whether additional digital canopy height model data can improve training. While the latter is shown to have no, if not a negative impact on the results, Mask2Former indeed outperforms Mask R-CNN in tree instance segmentation by up to 3.8%. Our code is publicly available.2 KW - individual tree crown delineation KW - instance segmentation KW - Mask2Former ER - TY - JOUR TI - Project VoLL-KI : Learning from Learners AU - Kohlhase, Michael AU - Berges, Marc AU - Grubert, Jens AU - Landes, Dieter AU - Leidner, Jochen L. AU - Henrich, Andreas AU - Mittag, Florian AU - Nicklas, Daniela AU - Schmid, Ute Maria AU - Sedlmaier, Yvonne AU - Ulbrich-vom Ende, Achim AU - Wolter, Diedrich PY - 2026 VL - 39 SP - 299–309 PB - Otto-Friedrich-Universität CY - Bamberg UR - https://fis.uni-bamberg.de/handle/uniba/115195 LA - eng AB - “Learning from Learners” (“Von Lernenden Lernen”, “VoLL-KI ” for short) is a is collaborative research project with the goal of creating a practical toolbox of instruments at diferent levels of abstraction to improve the learning experience and outcomes for students of artifcial intelligence. Learning and teaching at tertiary education institutions are currently ITbased but not AI-supported. The VoLL-KI project aims to go this crucial next step. Using AI approaches (e.g., ML, symbolic AI, statistical AI), several educational technologies are developed on the diferent granularity of the study programs (e.g., course, semester, program). So, dashboards for study planning, recommender systems improving student advisory services and learning material selection, VR-based learning experiences, educational chatbots, and adaptive learning environments are developed. The systems are mostly deployed as prototypes KW - Computer-aided education KW - Intelligent tutoring systems KW - Teaching support for artifcial intelligence education KW - Computer-aided learning (CAL) KW - Data-driven learning quality management KW - Study course monitoring KW - Learning analytics ER - TY - CHAP TI - Trustworthy Artificial Intelligence : Comprehensible, Transparent and Correctable AU - Schmid, Ute Maria PY - 2026 SP - 151-164 PB - Otto-Friedrich-Universität CY - Bamberg UR - https://fis.uni-bamberg.de/handle/uniba/115178 LA - eng AB - With the digital transformation, artificial intelligence (AI) applications are also finding their way into more and more areas of work and life. In particular, models learned from data are being used, which are mostly opaque black boxes. The fact that people can understand why an AI system behaves the way it does is necessary for various reasons: The model developers themselves must be able to assess properties of the learned models—in particular, possible biases due to overfitting to the data used for learning. For safety-critical applications, aspects of certification and testing are also becoming increasingly relevant. Domain experts— for example, in medical diagnostics or quality control in industrial production—must be able to comprehend, verify and, if necessary, correct system decisions. Consumers should understand why a system—a smart home control, a driving assistance—behaves in a certain way and why they are recommended certain products, offered certain tariffs or denied certain offers. After a brief introduction to the topic of AI, the chapter gives an overview of methods of the so-called third wave of AI. Central to this are approaches of explainable AI (XAI), which are intended to make the decisions of AI systems comprehensible. The main approaches are characterized and shown for which objectives and applications they are suitable in each case. It is shown that in addition to the highly regarded methods for visualization, methods that allow system decisions to be described in a differentiated manner are also particularly important. It is also argued that, in addition to comprehensibility, interactivity and correctability of AI systems are necessary so that AI systems do not restrict human competences but support them in partnership. ER - TY - JOUR TI - Explainable and interpretable machine learning and data mining AU - Atzmueller, Martin AU - Fürnkranz, Johannes AU - Kliegr, Tomáš AU - Schmid, Ute PY - 2026 SP - 2571-2595 PB - Otto-Friedrich-Universität CY - Bamberg UR - https://fis.uni-bamberg.de/handle/uniba/115177 LA - eng AB - The growing number of applications of machine learning and data mining in many domains—from agriculture to business, education, industrial manufacturing, and medicine—gave rise to new requirements for how to inspect and control the learned models. The research domain of explainable artifcial intelligence (XAI) has been newly established with a strong focus on methods being applied post-hoc on blackbox models. As an alternative, the use of interpretable machine learning methods has been considered—where the learned models are white-box ones. Black-box models can be characterized as representing implicit knowledge—typically resulting from statistical and neural approaches of machine learning, while white-box models are explicit representations of knowledge—typically resulting from rule-learning approaches. In this introduction to the special issue on ‘Explainable and Interpretable Machine Learning and Data Mining’ we propose to bring together both perspectives, pointing out commonalities and discussing possibilities to integrate them. KW - Explainable AI KW - Explainable and interpretable machine learning KW - Explainable and interpretable data mining KW - Hybrid artifcial intelligence ER - TY - JOUR TI - Toward human-level concept learning : Pattern benchmarking for AI algorithms AU - Holzinger, Andreas AU - Saranti, Anna AU - Angerschmid, Alessa AU - Finzel, Bettina AU - Schmid, Ute AU - Mueller, Heimo PY - 2026 SP - 1-21 PB - Otto-Friedrich-Universität CY - Bamberg UR - https://fis.uni-bamberg.de/handle/uniba/114970 LA - eng AB - Artificial intelligence (AI) today is very successful at standard pattern-recognition tasks due to the availability of large amounts of data and advances in statistical data-driven machine learning. However, there is still a large gap between AI pattern recognition and human-level concept learning. Humans can learn amazingly well even under uncertainty from just a few examples and are capable of generalizing these concepts to solve new conceptual problems. The growing interest in explainable machine intelligence requires experimental environments and diagnostic/benchmark datasets to analyze existing approaches and drive progress in pattern analysis and machine intelligence. In this paper, we provide an overview of current AI solutions for benchmarking concept learning, reasoning, and generalization; discuss the state-of-the-art of existing diagnostic/ benchmark datasets (such as CLEVR, CLEVRER, CLOSURE, CURI, Bongard-LOGO, V-PROM, RAVEN, Kandinsky Patterns, CLEVR-Humans, CLEVRER-Humans, and their extension containing human language); and provide an outlook of some future research directions in this exciting research domain. ER - TY - CPAPER TI - A Framework for Context-aware XAI in Human-AI Collaboration AU - Knoblach, Judith AU - Finzel, Bettina AU - Schmid, Ute PY - 2026 T2 - Contextualizing Explanations : Proceedings of the 3rd TRR 318 Conference SP - 24 PB - Bielefeld University Press CY - Bielefeld DO - 10.64136/deef2831 UR - https://fis.uni-bamberg.de/handle/uniba/114752 LA - eng ER - TY - CHAP TI - Künstliche Intelligenz in der Grundschule AU - Weitz, Katharina AU - Schmid, Ute PY - 2026 T2 - Informatische Bildung in der Grundschule SP - 122-146 PB - Kohlhammer CY - Stuttgart SN - 978-3-17-040748-0 DO - 10.17433/978-3-17-040749-7 UR - https://fis.uni-bamberg.de/handle/uniba/114321 LA - deu ER - TY - CHAP TI - Die Experimentierkiste Elementarinformatik zur Förderung informatischer Kompetenzen in der Vor- und Grundschule AU - Gärtig-Daugs, Anja AU - Schmid, Ute Maria AU - Weitz, Katharina PY - 2026 T2 - Informatische Bildung in der Grundschule SP - 77-99 PB - Kohlhammer CY - Stuttgart DO - 10.17433/978-3-17-040749-7 UR - https://fis.uni-bamberg.de/handle/uniba/114320 LA - deu ER - TY - BOOK TI - Informatische Bildung in der Grundschule AU - Pohlmann-Rother, Sanna AU - Jocham, Tina AU - Schmid, Ute Maria AU - Lange, Sarah AU - Gärtig-Daugs, Anja PY - 2026 PB - Kohlhammer Verlag CY - Stuttgart T3 - Grundschule heute SN - 978-3-17-040749-7 DO - 10.17433/978-3-17-040749-7 UR - https://fis.uni-bamberg.de/handle/uniba/114317 LA - deu ER - TY - CHAP TI - Vertrauenswürdige Künstliche Intelligenz AU - Schmid, Ute Maria PY - 2026 SP - 191-210 PB - Otto-Friedrich-Universität CY - Bamberg UR - https://fis.uni-bamberg.de/handle/uniba/113192 LA - deu AB - Für die sichere und sinnvolle Anwendung von KI-Systemen, insbesondere solchen, die auf komplexen, aus Daten gelernten Modellen basieren, müssen KI-Systeme vertrauenswürdig sein und Anwendende in die Lage versetzt werden, die Vertrauenswürdigkeit einschätzen zu können. Anforderungen an Vertrauenswürdige KI sind insbesondere Performanz und Robustheit, Transparenz und Erklärbarkeit, Diskriminierungsfreiheit sowie menschliche Kontrolle und Aufsicht. Um diese Anforderungen zu erfüllen, werden in der KI-Forschung Methoden entwickelt, die die Kernmethoden des maschinellen Lernens erweitern. Damit Nutzende ihr Vertrauen in KI-Systeme sinnvoll kalibrieren können, müssen die Schnittstellen zwischen KI-System und Mensch so gestaltet sein, dass die Ausgabe eines KI-Systems fundiert bewertet und gegebenenfalls korrigiert werden kann. Auf dieser Grundlage können partnerschaftliche KI-Systeme entwickelt werden, die Menschen dabei unterstützen, komplexe Probleme effizient und angemessen zu lösen. KW - - ER - TY - CHAP TI - Ein Intelligentes Tutorielles System zur Förderung des Computational Thinking am Beispiel von Sortieraufgaben mit Bubblesort AU - Münsterberg, Alisa Veronique AU - Schmid, Ute PY - 2026 T2 - Informatische Bildung in der Grundschule SP - 100-121 PB - Kohlhammer Verlag CY - Stuttgart ET - 1 SN - 978-3-17-040750-3 UR - https://fis.uni-bamberg.de/handle/uniba/114249 LA - deu ER - TY - CPAPER TI - Towards Observing the Effect of Abstraction on Understandability of Explanations in Answer Set Programming AU - Saribatur, Zeynep G. AU - Langer, Johannes AU - Thaler, Anna Magdalena AU - Schmid, Ute PY - 2026 T2 - KI 2025: advances in artificial intelligence : 48th German Conference on AI, Potsdam, Germany, September 16-19, 2025, proceedings SP - 236-243 PB - Springer CY - Cham SN - 978-3-032-02813-6 DO - 10.1007/978-3-032-02813-6_18 UR - https://fis.uni-bamberg.de/handle/uniba/113679 LA - eng ER - TY - CPAPER TI - Tagungsband der Zweiten Tagung KI und Bildung zusammen mit dem Praxistag KI an Schulen (KIBIS 2025) AU - Schmid, Ute AU - Weiss, Eva-Maria AU - Münsterberg, Alisa Veronique AU - Haase, Felix AU - Grabisch, Sanne AU - Schneider, Steffen AU - Michaeli, Tilman AU - Hauck-Thum, Uta AU - Baumer, Sven AU - Jetzinger, Franz AU - Gebhardt, Luisa AU - Grelka, Felix AU - Berges, Marc AU - Vollhardt, Jonas AU - Zimmerer, Chris AU - Wienrich, Carolin AU - Lange, Sarah Desiree AU - Marx, Erik AU - Görel, Gamze AU - Plohmer, Anna AU - Bergner, Nadine AU - Pohlmann-Rother, Sanna AU - Irion, Thomas AU - Lindner, Annabel AU - Steltmann, Luca Sebastian AU - Jansohn, Eva AU - Völker, Adrian AU - Vu, Mai Anh AU - Paukner, Franziska AU - Oehlhorn, Caroline AU - Wessendorf, Jona AU - Dannath, Jesper AU - Paaßen, Benjamin AU - Redlich, Jan-Philipp AU - Diekmann, Susanne AU - Zoeger, Viktoria AU - Rörich, Anna AU - Tölken, Sabrina AU - Hofmann, Bianka AU - Müller, Matthias AU - Müller-Unterweger, Michaela AU - Kunkel, Oliver AU - Ade, Larissa AU - Kindermann, Katharina AU - Jäger, Anne-Kathrin AU - Schmidt, Sebastian AU - Seiller, Pia-Maria AU - Stöhr, Ingrid ED - Schmid, Ute ED - Münsterberg, Alisa Veronique ED - Weiss, Eva-Maria PY - 2026 PB - University of Bamberg Press CY - Bamberg T3 - Schriften aus der Fakultät Wirtschaftsinformatik und Angewandte Informatik der Otto-Friedrich-Universität Bamberg SN - 978-3-98989-075-6 DO - 10.20378/irb-112219 UR - https://fis.uni-bamberg.de/handle/uniba/112219 LA - other AB - Das Thema Künstliche Intelligenz (KI) gewinnt zunehmend Bedeutung im Bildungsbereich. Zum einen ist die Vermittlung grundlegender Kompetenzen im Bereich KI (AI Literacy) als Erweiterung von Medien- und Informatikkompetenzen relevant, um einen sicheren und reflektierten Umgang mit KI-Systemen zu ermöglichen. Zum anderen werden neue, KI-basierte Ansätze zur Unterstützung von Lehr- und Lernprozessen erforscht und entwickelt. Die Gestaltung von Bildungsprozessen in Schule, Hochschule, Ausbildung und im außerschulischen Bereich kann nur gelingen, wenn Wissenschaft und Anwendung zusammenarbeiten, um relevante fachliche Kompetenzen im Kontext der zunehmenden Verfügbarkeit von KI-Werkzeugen zu identifizieren und daraus Anforderungen an KI-Systeme im Bildungsbereich abzuleiten. Genau dies ist das Anliegen der Tagung “Künstliche Intelligenz in der Bildung zusammen mit dem Praxistag KI an Schulen” (KIBIS 2025), die am 9. und 10.Oktober 2025 zum zweiten Mal an der Universität Bamberg stattgefunden hat. Der Tagungsband der KIBIS 2025 umfassen Forschungsbeiträge aus den Bereichen KI, Informatikdidaktik, Fachdidaktiken und Pädagogik zur Vermittlung von KI-Kompetenzen für unterschiedliche Zielgruppen. Vertreterinnen und Vertreter aus der Bildungspraxis in Schule, Hochschule, im betrieblichen und außerschulischen Bereich stellen konkrete Anwendungen der KI-Vermittlung sowie beim Einsatz von KI-Werkzeugen vor. KW - AI & Education KW - KI-Bildung ER - TY - CPAPER TI - Human-AI Collaboration in Coding : A Trust Perspective AU - Niemann, Sonja AU - Schmid, Ute PY - 2025 VL - 84 PB - Techn. Univ. CY - Berlin SN - 1863-2122 DO - 10.14279/eceasst.v84.2679.g2784 UR - https://fis.uni-bamberg.de/handle/uniba/117280 LA - eng AB - Generative AI (GenAI) is transforming software development and Computer Science (CS) education, raising critical questions about trust in human-AI collaboration. This paper examines trust in GenAI from interdisciplinary perspectives, assessing existing trust frameworks and their applicability. Seemingly contradictory definitions and approaches are discussed and a solution is presented that could resolve the contradictions. We explore how trust affects adoption in education and software development, reviewing measurement approaches and implications for calibrated trust. Our findings highlight the gap between theoretical trust and practical reliance, contributing to the discourse on AI usability and integration. KW - Generative AI KW - Trust KW - Trustworthy KW - Human-AI Collaboration ER - TY - CHAP TI - The Impact of Peers, Mentors and Role Models on Successful PhD Studies AU - Knoblach, Judith AU - Schmid, Ute AU - Goulão, Miguel AU - Schmid, Larissa AU - Vujošević Janičić, Milena AU - Boudaoud, Karima PY - 2025 T2 - Actions for Gender Balance in Informatics Across Europe SP - 175-195 PB - Springer Nature Switzerland CY - Cham SN - 9783031784316 DO - 10.1007/978-3-031-78432-3_8 UR - https://fis.uni-bamberg.de/handle/uniba/116781 LA - eng ER - TY - CPAPER TI - Interactive Explainable Anomaly Detection for Industrial Settings AU - Gramelt, Daniel AU - Höfer, Timon AU - Schmid, Ute PY - 2025 T2 - Computer vision - ECCV 2024 workshops Milan, Italy, September 29-October 4, 2024, proceedings, part IV SP - 133-147 PB - Springer Nature Switzerland CY - Cham, Switzerland SN - 9783031928048 DO - 10.1007/978-3-031-92805-5_9 UR - https://fis.uni-bamberg.de/handle/uniba/116709 LA - eng ER - TY - JOUR TI - Was alle über Künstliche Intelligenz wissen sollen und wie KI-bezogene Kompetenzen in der Schule entwickelt werden können : Weiterführende Überlegungen zum GI-Positionspapier „Künstliche Intelligenz in der Bildung“ AU - Losch, Danie AU - Jaschke, Steffen AU - Michaeli, Tilman AU - Opel, Simone AU - Schmid, Ute AU - Seegerer, Stefan AU - Stechert, Peer PY - 2025 JO - Informatik-Spektrum : Organ der Gesellschaft für Informatik e.V. VL - 48 SP - 38–46 PB - Springer CY - Berlin ; Heidelberg ; New York SN - 1432-122X DO - 10.1007/s00287-024-01584-w UR - https://fis.uni-bamberg.de/handle/uniba/116650 LA - deu AB - Aufbauend auf dem Positionspapier der Gesellschaft für Informatik zur Bedeutung von Künstlicher Intelligenz (KI) in der Bildung wird im Beitrag die Notwendigkeit diskutiert, Schüler*innen sowie Lehrkräfte auf die Chancen und Herausforderungen von KI vorzubereiten. Es werden verschiedene Ansätze zum Lehren und Lernen über und mit KI vorgestellt, darunter die Integration von KI in den Informatikunterricht, die Verwendung von Unplugged-Ansätzen und die Entwicklung von KI-bezogenen Kompetenzen in der berufichen Bildung. Der Beitrag betont die Bedeutung von Informatik als Pfichtfach im allgemeinbildenden Unterricht. Abschließend werden die Konsequenzen von KI für die Bildung und die Notwendigkeit eines interdisziplinären Diskurses über die Gestaltung von Bildung in einer digital geprägten Welt diskutiert. KW - - ER - TY - BOOK TI - Kognitive Künstliche Intelligenz AU - Ragni, Marco AU - Schmid, Ute PY - 2025 PB - Springer Berlin Heidelberg CY - Berlin SN - 978-3-662-69497-8 DO - 10.1007/978-3-662-69498-5 UR - https://fis.uni-bamberg.de/handle/uniba/115618 LA - deu ER - TY - CPAPER TI - Toward Simple and Robust Contrastive Explanations for Image Classification by Leveraging Instance Similarity and Concept Relevance AU - Kaidashova, Yuliia AU - Finzel, Bettina AU - Schmid, Ute Maria ED - Springer Nature Switzerland PY - 2025 T2 - KI 2025: advances in artificial intelligence : 48th German Conference on AI, Potsdam, Germany, September 16-19, 2025, proceedings SP - 32-46 PB - Springer Nature Switzerland CY - Cham SN - 978-3-032-02812-9 DO - 10.1007/978-3-032-02813-6_3 UR - https://fis.uni-bamberg.de/handle/uniba/113752 LA - eng ER - TY - JOUR TI - Aligning generalization between humans and machines AU - Ilievski, Filip AU - Hammer, Barbara AU - van Harmelen, Frank AU - Paaßen, Benjamin AU - Saralajew, Sascha AU - Schmid, Ute Maria AU - Biehl, Michael AU - Bolognesi, Marianna AU - Dong, Xin Luna AU - Gashteovski, Kiril AU - Hitzler, Pascal AU - Marra, Giuseppe AU - Minervini, Pasquale AU - Mundt, Martin AU - Ngomo, Axel-Cyrille Ngonga AU - Oltramari, Alessandro AU - Pasi, Gabriella AU - Saribatur, Zeynep G. AU - Serafini, Luciano AU - Shawe-Taylor, John AU - Shwartz, Vered AU - Skitalinskaya, Gabriella AU - Stachl, Clemens AU - van de Ven, Gido M. AU - Villmann, Thomas PY - 2025 JO - Nature Machine Intelligence VL - 7 IS - 9 SP - 1378–1389 PB - Springer Nature Publishing CY - London SN - 2522-5839 DO - 10.1038/s42256-025-01109-4 UR - https://fis.uni-bamberg.de/handle/uniba/113755 LA - eng ER - TY - RPRT TI - Nachvollziehbare KI : Erklären, für wen, was und wofür AU - Samek, Wojciech AU - Schmid, Ute AU - Hoffart, Johannes AU - Keim, Daniel AU - Kutyniok, Gitta AU - Schlunder, Philipp PY - 2025 CY - München DO - 10.48669/pls_2025-2 UR - https://fis.uni-bamberg.de/handle/uniba/113754 LA - deu ER - TY - CPAPER TI - Teaching Programming in Primary School : Unplugged or Plugged-In First? AU - Münsterberg, Alisa Veronique AU - Schmid, Ute Maria AU - Grabisch, Sanne AU - Langer, Johannes AU - Troles, Jonas PY - 2025 T2 - ICERI 2025 proceedings : 18th Annual International Conference of Education, Research and Innovation Seville, Spain, 10-12 November, 2025 SP - 5440-5449 PB - IATED Academy CY - Valencia, Spain SN - 978-84-09-78706-7 DO - 10.21125/iceri.2025.1518 UR - https://fis.uni-bamberg.de/handle/uniba/112228 LA - eng ER - TY - JOUR TI - FMC-Net : A Human-Guided Deep Learning Framework for Adaptable and Transparent Facial Expression Recognition in Real-World Scenarios AU - Rieger, Ines AU - Pahl, Jasper AU - Schmid, Ute PY - 2025 SP - 1-19 PB - Otto-Friedrich-Universität CY - Bamberg UR - https://fis.uni-bamberg.de/handle/uniba/112139 LA - eng AB - We introduce FMC-Net, a facial expression recognition (FER) framework that leverages the hierarchical relationship between discrete facial muscle movements, known as Action Units (AUs), and Facial Expressions (FEs) by integrating two complementary constraint layers. This framework couples data-driven learning with psychology-grounded structure. First, a training-time correlation constraint aligns the two tasks within a multi-task network by softly regularizing a target statistical relationship. This can improve sample efficiency and generalization, particularly under limited or biased data. Second, an inference-time fuzzy rule layer maps the networks probabilistic AU predictions to FEs using compact, human-editable from psychological research, yielding transparent, per-decision attributions. An ensemble then combines the model and rule-based pathways and exposes a disagreement-based risk score for human-in-the-loop triage. This two-layer constraint integration addresses the limitations of single-mechanism approaches: training-time constraints shape the learned representations but lack case-wise transparency, while inference-time rules explain decisions but cannot improve the underlying features. Experiments across diverse datasets, including in-the-wild video and cross-dataset evaluation, validate our approach. Constraint-guided training consistently produces models that outperform competitive baselines, while the rule-based pathway can provide transparency and actionable risk signals towards reliable deployment. The proposed methodology is also generalizable to other machine learning tasks with interdependent outputs. KW - Deep learning KW - Facial expression recognition KW - Constraint integration KW - Human-guided AI ER - TY - JOUR TI - FMC-Net : A Human-Guided Deep Learning Framework for Adaptable and Transparent Facial Expression Recognition in Real-World Scenarios AU - Rieger, Ines AU - Pahl, Jasper AU - Schmid, Ute PY - 2025 JO - Applied intelligence : the international journal of artificial intelligence, neural networks, and complex problem-solving technologies VL - 55 IS - 18, 1127 SP - 1-19 PB - Springer Science + Business Media B.V CY - Dordrecht [u.a.] SN - 1573-7497 DO - 10.1007/s10489-025-07017-9 UR - https://fis.uni-bamberg.de/handle/uniba/112138 LA - eng AB - We introduce FMC-Net, a facial expression recognition (FER) framework that leverages the hierarchical relationship between discrete facial muscle movements, known as Action Units (AUs), and Facial Expressions (FEs) by integrating two complementary constraint layers. This framework couples data-driven learning with psychology-grounded structure. First, a training-time correlation constraint aligns the two tasks within a multi-task network by softly regularizing a target statistical relationship. This can improve sample efficiency and generalization, particularly under limited or biased data. Second, an inference-time fuzzy rule layer maps the networks probabilistic AU predictions to FEs using compact, human-editable from psychological research, yielding transparent, per-decision attributions. An ensemble then combines the model and rule-based pathways and exposes a disagreement-based risk score for human-in-the-loop triage. This two-layer constraint integration addresses the limitations of single-mechanism approaches: training-time constraints shape the learned representations but lack case-wise transparency, while inference-time rules explain decisions but cannot improve the underlying features. Experiments across diverse datasets, including in-the-wild video and cross-dataset evaluation, validate our approach. Constraint-guided training consistently produces models that outperform competitive baselines, while the rule-based pathway can provide transparency and actionable risk signals towards reliable deployment. The proposed methodology is also generalizable to other machine learning tasks with interdependent outputs. KW - Deep learning KW - Facial expression recognition KW - Constraint integration KW - Human-guided AI ER - TY - CPAPER TI - Data literacy in primary school teachers’ education and training AU - Gärtig-Daugs, Anja AU - Werner, Alexander AU - Troles, Jonas AU - Schneider, Adrian AU - Szczepaniak, Renata AU - Schmid, Ute PY - 2025 PB - Otto-Friedrich-Universität CY - Bamberg UR - https://fis.uni-bamberg.de/handle/uniba/112061 LA - eng AB - The growing relevance of data-driven technologies in children’s everyday lives highlights the need to introduce fundamental data literacy concepts in primary education. To achieve this, primary school teachers must possess adequate data skills and know how to teach them effectively. A Massive Open Online Course (MOOC) was therefore developed to provide (prospective) primary school teachers with essential data literacy competencies, covering basic concepts, data evaluation and security, and introductory machine learning, complemented by ready-to-use teaching materials. Preliminary results from an ongoing evaluation show that participants are highly motivated, consider data literacy important for both their personal and professional lives, and generally rate their prior knowledge as moderate. Despite this, most feel capable of conveying data literacy after completing the course. These findings suggest that a MOOC is a suitable way to integrate data literacy into teacher education and to support its implementation in primary school classrooms. KW - data literacy KW - teacher education KW - massive online open course KW - teacher professionalisation ER - TY - JOUR TI - Knowledge graph enhanced retrieval-augmented generation for failure mode and effects analysis AU - Bahr, Lukas AU - Wehner, Christoph AU - Wewerka, Judith AU - Bittencourt, José AU - Schmid, Ute AU - Daub, Rüdiger PY - 2025 SP - 1-9 PB - Otto-Friedrich-Universität CY - Bamberg UR - https://fis.uni-bamberg.de/handle/uniba/111079 LA - eng AB - Failure mode and effects analysis (FMEA) is an essential tool for mitigating potential failures, particularly during the ramp-up phases of new products. However, its effectiveness is often limited by the reasoning capabilities of the FMEA tools, which are usually tabular structured. Meanwhile, large language models (LLMs) offer novel prospects for advanced natural language processing tasks. However, LLMs face challenges in tasks that require factual knowledge, a gap that retrieval-augmented generation (RAG) approaches aim to fill. RAG retrieves information from a non-parametric data store and uses a language model to generate responses. Building on this concept, we propose to enhance the non-parametric data store with a knowledge graph (KG). By integrating a KG into the RAG framework, we aim to leverage analytical and semantic question-answering capabilities for FMEA data. This paper contributes by presenting set-theoretic standardization and a schema for FMEA data, an algorithm for creating vector embeddings from the FMEA-KG, and a KG-enhanced RAG framework. Our approach is validated through a user experience design study, and we measure the precision and performance of the context retrieval recall. KW - FMEA KW - Risk assessment KW - Knowledge graph KW - Retrieval-augmented generation KW - Large language models ER - TY - JOUR TI - Beneficial and harmful explanatory machine learning AU - Ai, Lun AU - Muggleton, Stephen H. AU - Hocquette, Céline AU - Gromowski, Mark AU - Schmid, Ute PY - 2025 SP - 695-721 PB - Otto-Friedrich-Universität CY - Bamberg UR - https://fis.uni-bamberg.de/handle/uniba/109790 LA - eng AB - Given the recent successes of Deep Learning in AI there has been increased interest in the role and need for explanations in machine learned theories. A distinct notion in this context is that of Michie’s definition of ultra-strong machine learning (USML). USML is demonstrated by a measurable increase in human performance of a task following provision to the human of a symbolic machine learned theory for task performance. A recent paper demonstrates the beneficial effect of a machine learned logic theory for a classification task, yet no existing work to our knowledge has examined the potential harmfulness of machine’s involvement for human comprehension during learning. This paper investigates the explanatory effects of a machine learned theory in the context of simple two person games and proposes a framework for identifying the harmfulness of machine explanations based on the Cognitive Science literature. The approach involves a cognitive window consisting of two quantifiable bounds and it is supported by empirical evidence collected from human trials. Our quantitative and qualitative results indicate that human learning aided by a symbolic machine learned theory which satisfies a cognitive window has achieved significantly higher performance than human self learning. Results also demonstrate that human learning aided by a symbolic machine learned theory that fails to satisfy this window leads to significantly worse performance than unaided human learning. KW - Critical Thinking KW - Instructional Theory KW - Learning Theory KW - Machine Learning KW - Symbolic AI KW - Artificial Intelligence ER - TY - CPAPER TI - Fostering data and AI competencies in primary schools AU - Gärtig-Daugs, Anja AU - Schmid, Ute PY - 2025 SP - 1-5 PB - Otto-Friedrich-Universität CY - Bamberg UR - https://fis.uni-bamberg.de/handle/uniba/111340 LA - eng AB - Data-driven tools and AI applications are present in the daily lives of young children. In Germany, one central objective of education policy is to support children in exploring, understanding and shaping the digital world through appropriate educational programs. However, many teachers lack data and AI competencies. In order to forster the integration of data and AI topics in primary school lessons, we designed a massive open online course for the qualification of primary school teachers.The course either can be integrated in a blended-learning format in university courses or can be self-paced followed by professional teachers. It requires no prior knowledge and provides teaching and learning materials for the forstering of data and AI competencies in different primary school subjects. KW - AI and data science curricula and implementation in schools KW - learning materials ER - TY - CPAPER TI - Fostering data and AI competencies in primary schools AU - Gärtig-Daugs, Anja AU - Schmid, Ute PY - 2025 T2 - Towards Fostering AI and Data Science Literacy in Schools Across Disciplines : Proceedings of the 1st Symposium on Integrating AI and Data Science into School Education Across Disciplines (AIDEA1 2025) SP - 1-5 UR - https://fis.uni-bamberg.de/handle/uniba/111601 LA - eng AB - Data-driven tools and AI applications are present in the daily lives of young children. In Germany, one central objective of education policy is to support children in exploring, understanding and shaping the digital world through appropriate educational programs. However, many teachers lack data and AI competencies. In order to forster the integration of data and AI topics in primary school lessons, we designed a massive open online course for the qualification of primary school teachers.The course either can be integrated in a blended-learning format in university courses or can be self-paced followed by professional teachers. It requires no prior knowledge and provides teaching and learning materials for the forstering of data and AI competencies in different primary school subjects. KW - AI and data science curricula and implementation in schools KW - learning materials ER - TY - JOUR TI - Time to Forget : Intentional Forgetting in the Digital World of Work AU - Niessen, Cornelia AU - Göbel, Kyra AU - Siebers, Michael AU - Schmid, Ute PY - 2025 VL - 64 IS - 1 SP - 30-45 PB - Otto-Friedrich-Universität CY - Bamberg UR - https://fis.uni-bamberg.de/handle/uniba/110278 LA - eng AB - Emerging technologies at work encourage the collection and storage of large amounts of data. However, these vast quantities of data are likely to impair efficient work decisions by employees over time, with negative consequences for the organization. As human attention increasingly represents the scarce resource at work, the present paper focuses on a mechanism of attentional control at work – namely, intentionally forgetting unwanted and outdated internal (e. g., knowledge) and external (e. g., digital objects) information. The purpose of this paper is threefold. Based on a short review of the research on intentional forgetting, a prototypical conceptualization of an interactive assistive system (Dare2Del, cognitive companion) is provided, which should support employees in temporally ignoring or permanently deleting outdated information. Then, we completed a critical incident study to examine why and when employees might want to forget information at work, and to identify in which working situations an assistive system should be particularly helpful. KW - information overload KW - intentional forgetting KW - self-control ER - TY - CPAPER TI - Perzeptrons programmieren und explorieren im Rahmen der Open Roberta Lernumgebung AU - Münsterberg, Alisa Veronique AU - Budde, Reinhard AU - Leimbach, Thorsten AU - Schmid, Ute PY - 2025 SP - 435-436 PB - Otto-Friedrich-Universität CY - Bamberg UR - https://fis.uni-bamberg.de/handle/uniba/110317 LA - deu AB - Die Lowcode Robotics Platform OpenRoberta Lab wurde um Bausteine zur Programmierung von Perzeptronen erweitert. Damit wird die Möglichkeit geschaffen, dass Kinder dieGrundprinzipien des maschinellen Lernens als Generalisierung über Beispiele direkt umsetzen und interaktiv explorieren können. KW - Programmierplattform; KW - Maschinelles Lernen KW - Interaktives Lernen ER - TY - GEN TI - Comprehensible Artificial Intelligence on Knowledge Graphs : A survey AU - Schramm, Simon AU - Wehner, Christoph AU - Schmid, Ute PY - 2025 SP - 1-23 PB - Otto-Friedrich-Universität CY - Bamberg UR - https://fis.uni-bamberg.de/handle/uniba/110308 LA - eng AB - Artificial Intelligence applications gradually move outside the safe walls of research labs and invade our daily lives. This is also true for Machine Learning methods on Knowledge Graphs, which has led to a steady increase in their application since the beginning of the 21st century. However, in many applications, users require an explanation of the Artificial Intelligences decision. This led to increased demand for Comprehensible Artificial Intelligence. Knowledge Graphs epitomize fertile soil for Comprehensible Artificial Intelligence, due to their ability to display connected data, i.e. knowledge, in a human- as well as machine-readable way. This survey gives a short history to Comprehensible Artificial Intelligence on Knowledge Graphs. Furthermore, we contribute by arguing that the concept Explainable Artificial Intelligence is overloaded and overlapping with Interpretable Machine Learning. By introducing the parent concept Comprehensible Artificial Intelligence, we provide a clear-cut distinction of both concepts while accounting for their similarities. Thus, we provide in this survey a case for Comprehensible Artificial Intelligence on Knowledge Graphs consisting of Interpretable Machine Learning on Knowledge Graphs and Explainable Artificial Intelligence on Knowledge Graphs. This leads to the introduction of a novel taxonomy for Comprehensible Artificial Intelligence on Knowledge Graphs. In addition, a comprehensive overview of the research on Comprehensible Artificial Intelligence on Knowledge Graphs is presented and put into the context of the taxonomy. Finally, research gaps in the field of Comprehensible Artificial Intelligence on Knowledge Graphs are identified for future research. KW - Comprehensible Artificial Intelligence ER - TY - CPAPER TI - AI Literacy : Why Basic Understanding of AI Methods is Relevant for Safe, Efficient, and Reflected Use of AI-Tools AU - Schmid, Ute PY - 2025 SP - 1-34 PB - Otto-Friedrich-Universität CY - Bamberg DO - 10.20378/irb-110824 UR - https://fis.uni-bamberg.de/handle/uniba/110824 LA - eng AB - With the growing number of AI-Tools in many domains, AI literacy is essential for their save, efficient and reflected use. Often, AI literacy has a focus on the usage of tools. In my talk, I will argue why a theoretical understanding of basic principles of AI methods is an important prerequisite for tool use as well as for critical reflections of effects of AI technologies on society and environment. The major challenge in communicating AI concepts to laypeople is to convey technically correct information that is at the same time didactically tailored to the target group. In the talk, I will introduce basic AI concepts together with illustrations how these concepts can be taught. Furthermore, I will point out typical pitfalls for misjudgments that are based on an inadmissible anthropomorphization of AI. KW - Künstliche Intelligenz KW - Artificial Intelligence KW - Informationskompetenz KW - KI-Kompetenz KW - Information Literacy KW - AI Literacy ER - TY - JOUR TI - KI-Tools : Wie können wir ihre Potenziale in der Bildung für eine Stärkung der Bildungsgerechtigkeit und Chancengleichheit nutzen AU - Schmid, Ute AU - Weiss, Eva-Maria PY - 2025 JO - Bildung, Chancen, Wandel VL - 1 IS - 7 SP - 10-12 PB - BFA CY - Düsseldorf SN - 3052-8186 UR - https://fis.uni-bamberg.de/handle/uniba/110907 LA - deu ER - TY - CHAP TI - Vertrauenswürdige Künstliche Intelligenz AU - Schmid, Ute PY - 2025 T2 - Künstliche Intelligenz und Wir : Stand, Nutzung und Herausforderungen der KI SP - 191-210 PB - Springer CY - Berlin, Heidelberg SN - 978-3-662-71566-6 DO - 10.1007/978-3-662-71567-3_10 UR - https://fis.uni-bamberg.de/handle/uniba/110770 LA - deu AB - Für die sichere und sinnvolle Anwendung von KI-Systemen, insbesondere solchen, die auf komplexen, aus Daten gelernten Modellen basieren, müssen KI-Systeme vertrauenswürdig sein und Anwendende in die Lage versetzt werden, die Vertrauenswürdigkeit einschätzen zu können. Anforderungen an Vertrauenswürdige KI sind insbesondere Performanz und Robustheit, Transparenz und Erklärbarkeit, Diskriminierungsfreiheit sowie menschliche Kontrolle und Aufsicht. Um diese Anforderungen zu erfüllen, werden in der KI-Forschung Methoden entwickelt, die die Kernmethoden des maschinellen Lernens erweitern. Damit Nutzende ihr Vertrauen in KI-Systeme sinnvoll kalibrieren können, müssen die Schnittstellen zwischen KI-System und Mensch so gestaltet sein, dass die Ausgabe eines KI-Systems fundiert bewertet und gegebenenfalls korrigiert werden kann. Auf dieser Grundlage können partnerschaftliche KI-Systeme entwickelt werden, die Menschen dabei unterstützen, komplexe Probleme effizient und angemessen zu lösen. KW - - ER - TY - CPAPER TI - For What Tasks and Purpose Do Computer Science Students Use Code Generators : Preliminary Results of an Online-Study AU - Niemann, Sonja AU - Schmid, Ute PY - 2025 T2 - Proceedings of the Second Work shop on Artificial Intelligence for Artificial Intelligence Education (AI4AI Learning 2024) SP - 68-80 PB - University of Bamberg Press CY - Bamberg SN - 978-3-98989-054-1 DO - 10.20378/irb-108889 UR - https://fis.uni-bamberg.de/handle/uniba/108889 LA - eng AB - Generative AI is applied in different educational contexts such as essay writing or translation of texts. A specific application of generative models is creation of program code. Educators in schools and universities face the challenge how to assure that students acquire relevant competencies while making use of generative AI tools. In this paper, we present preliminary results of an online study of the use of code generators by Computer Science (CS) students. Beginner students get to learn basic programming concepts and skills, advanced students get to learn how to solve complex programming tasks and create programs which are correct, efficient, modifiable, and well documented. With the presented online study we want to explore which tasks students solve with code generators and with what purpose. 285 students participated in the survey, new beginners as well as advanced students, with the goal to compare students who learned programming basics without code generators with those who always had access to them. Preliminary results show that students are very eager to learn coding skills and want to understand underlying concepts. Students who struggle with coding skills tend to ask code generators more often for explanations and use code generators for the purpose of understanding. Students who chose not to use code generators are more skeptical of such systems and the mistakes they make. Our empirical results provide insights in how we can support students in acquiring coding skills while using code generators. KW - Code Generators KW - Programming Education KW - Programming Competencies ER - TY - CPAPER TI - Large Language Models as Domain-independent Dialogue Component for Intelligent Tutoring Systems – Teaching Concepts of SQL AU - Voelker, Adrian AU - Thaler, Anna Magdalena AU - Summerer, Maximilian T. AU - Schmid, Ute Maria PY - 2025 T2 - Proceedings of the Second Work shop on Artificial Intelligence for Artificial Intelligence Education (AI4AI Learning 2024) SP - 33-48 PB - University of Bamberg Press CY - Bamberg SN - 978-3-98989-054-1 DO - 10.20378/irb-108886 UR - https://fis.uni-bamberg.de/handle/uniba/108886 LA - eng AB - With the advance of generative pre-trained language models, new opportunities arise for domain-independent dialogue-based instruction in the context of intelligent tutoring systems (ITS). We propose an approach for combining large language models (LLMs) with domain-specific knowledge graphs to take advantage of the performance of LLMs in natural language processing tasks while still ensuring a faithful knowledge base. We present a prototypical implementation of an ITS for the structured query language SQL to explore the potential of combining LLM and domain specific knowledge graphs for dialogue based didactic intervention. While learning a programming language relies on both declarative knowledge about the language concepts and procedural knowledge for writing program code with respect to a specific task, in this paper we focus on ITS support for acquisition of declarative knowledge. In our implementation LLMs are employed for semantic parsing relating student’s questions to the addressed knowledge elements of the domain model as well as for feedback formulation based on retrieved information from the knowledge graph. Likewise, knowledge diagnosis is realized by semantic parsing of student answers and mapping them against the LLM output. We conducted a first exploratory evaluation using the LLM Mixtral 8x7B Instruct in combination with our SQL knowledge graph. Exploring different prompting strategies, the best strategy resulted in 90% correct diagnosis of student answers. KW - Intelligent Tutoring Systems KW - Large Language Models KW - Knowledge Graphs KW - SQL KW - Declarative Knowledge ER - TY - JOUR TI - FairCaipi : A Combination of Explanatory Interactive and Fair Machine Learning for Human and Machine Bias Reduction AU - Heidrich, Louisa AU - Slany, Emanuel AU - Scheele, Stephan M. AU - Schmid, Ute PY - 2025 SP - 1519-1538 PB - Otto-Friedrich-Universität CY - Bamberg UR - https://fis.uni-bamberg.de/handle/uniba/108494 LA - eng AB - The rise of machine-learning applications in domains with critical end-user impact has led to a growing concern about the fairness of learned models, with the goal of avoiding biases that negatively impact specific demographic groups. Most existing bias-mitigation strategies adapt the importance of data instances during pre-processing. Since fairness is a contextual concept, we advocate for an interactive machine-learning approach that enables users to provide iterative feedback for model adaptation. Specifically, we propose to adapt the explanatory interactive machine-learning approach Caipi for fair machine learning. FairCaipi incorporates human feedback in the loop on predictions and explanations to improve the fairness of the model. Experimental results demonstrate that FairCaipi outperforms a state-of-the-art pre-processing bias mitigation strategy in terms of the fairness and the predictive performance of the resulting machine-learning model. We show that FairCaipi can both uncover and reduce bias in machine-learning models and allows us to detect human bias. KW - fair machine learning KW - explanatory and interactive machine learning ER - TY - CPAPER TI - Proceedings of the Second Work shop on Artificial Intelligence for Artificial Intelligence Education (AI4AI Learning 2024) AU - Singla, Adish AU - Hobert, Sebastian AU - Joachim, Silvia AU - Hennecke, Martin AU - Voelker, Adrian AU - Thaler, Anna Magdalena AU - Summerer, Maximilian T. AU - Schmid, Ute AU - Bayerkuhnlein, Moritz AU - Wolter, Diedrich AU - Bugert, Flemming AU - Bittner, Dominik AU - Ezer, Timur AU - Nadimpalli, Vamsi Krishna AU - Staufer, Susanne AU - Hauser, Florian AU - Maier, Robert AU - Grabinger, Lisa AU - Mottok, Jürgen AU - Niemann, Sonja ED - Schmid, Ute Maria ED - Leidner, Jochen L. ED - Kohlhase, Michael ED - Wolter, Diedrich PY - 2025 PB - University of Bamberg Press CY - Bamberg T3 - Schriften aus der Fakultät Wirtschaftsinformatik und Angewandte Informatik der Otto-Friedrich-Universität Bamberg SN - 978-3-98989-054-1 DO - 10.20378/irb-107661 UR - https://fis.uni-bamberg.de/handle/uniba/107661 LA - eng AB - Artificial Intelligence (AI) methods for education have been a topic of AI research since many decades with focus on Intelligent Tutoring Systems (ITS). ITS typically address a specific knowledge domain with a focus on individual learning support based on learning by problem solving, identification of misconceptions, and tailored feedback. Methods often are a combination of knowledge-based and machine learning approaches. Since the emergence of technologies based on Large Language Models (LLMs), the use of LLMs in educational contexts has received much attention, resulting in novel approaches. The Second Workshop on Artificial Intelligence for Artificial Intelligence Education (AI4AILearning) has been held on September 24, 2024, in conjunction with the 47th German Conference on Artificial Intelligence in Würzburg, Germany. The workshop has a focus on research of AI methods for teaching AI competencies including programming skills. It provides a platform for exchange of ideas and experiences under the general theme of AI for education, specialising on university education in AI. The workshop includes interdisciplinary contributions from cognitive science and education technology. KW - AI Education KW - Programming Education KW - Technology-Enhanced-Learning KW - Intelligent Tutoring Systems KW - Large Language Models ER - TY - JOUR TI - BAMFORESTS : Bamberg Benchmark Forest Dataset of Individual Tree Crowns in Very-High-Resolution UAV Images AU - Troles, Jonas AU - Schmid, Ute Maria AU - Fan, Wen AU - Tian, Jiaojiao PY - 2025 SP - 1-12 PB - Otto-Friedrich-Universität CY - Bamberg UR - https://fis.uni-bamberg.de/handle/uniba/107687 LA - eng AB - The anthropogenic climate crisis results in the gradual loss of tree species in locations where they were previously able to grow. This leads to increasing workloads and requirements for foresters and arborists as they are forced to restructure their forests and city parks. The advancements in computer vision (CV)—especially in supervised deep learning (DL)—can help cope with these new tasks. However, they rely on large, carefully annotated datasets to produce good and generalizable models. This paper presents BAMFORESTS: a dataset with 27,160 individually delineated tree crowns in 105 ha of very-high-resolution UAV imagery gathered with two different sensors from two drones. BAMFORESTS covers four areas of coniferous, mixed, and deciduous forests and city parks. The labels contain instance segmentations of individual trees, and the proposed splits are balanced by tree species and vitality. Furthermore, the dataset contains the corrected digital surface model (DSM), representing tree heights. BAMFORESTS is annotated in the COCO format and is especially suited for training deep neural networks (DNNs) to solve instance segmentation tasks. BAMFORESTS was created in the BaKIM project and is freely available under the CC BY 4.0 license. KW - benchmark dataset KW - individual tree crown KW - instance segmentation KW - UAV imagery KW - tree species KW - forest ER - TY - CPAPER TI - Comparing Mask R-CNN and Mask2Former architectures for individual tree crown delineation AU - Ruschhaupt, Sonja AU - Troles, Jonas AU - Schmid, Ute PY - 2025 T2 - 45. GIL-Jahrestagung, Digitale Infrastrukturen für eine nachhaltige Land-, Forst-und Ernährungswirtschaft SP - 167-178 PB - Gesellschaft für Informatik e.V. CY - Bonn DO - 10.18420/giljt2025_13 UR - https://fis.uni-bamberg.de/handle/uniba/107281 LA - eng AB - Weather anomalies caused by the anthropogenic climate crisis challenge environmental workers such as foresters with an increasing number of responsibilities. In addition to providing attractive conditions for new generations of workers, deep-learning tools can ease processes for better efficiency. Tree instance segmentation has potential for many functionalities that support arborists and foresters by detecting and classifying singular trees. In the past, Mask R-CNN was primarily applied due to its outstanding performance on the 2016 COCO dataset challenge. As an alternative, we suggest Mask2Former, which outperforms Mask R-CNN on the COCO dataset. Additionally, we test whether additional digital canopy height model data can improve training. While the latter is shown to have no, if not a negative impact on the results, Mask2Former indeed outperforms Mask R-CNN in tree instance segmentation by up to 3.8%. Our code is publicly available.2 KW - individual tree crown delineation KW - instance segmentation KW - Mask2Former ER - TY - JOUR TI - Knowledge graph enhanced retrieval-augmented generation for failure mode and effects analysis AU - Bahr, Lukas AU - Wehner, Christoph AU - Wewerka, Judith AU - Bittencourt, José AU - Schmid, Ute AU - Daub, Rüdiger PY - 2025 JO - Journal of Industrial Information Integration VL - 45 IS - 100807 SP - 1-9 PB - Elsevier BV CY - Amsterdam SN - 2452-414X DO - 10.1016/j.jii.2025.100807 UR - https://fis.uni-bamberg.de/handle/uniba/107136 LA - eng AB - Failure mode and effects analysis (FMEA) is an essential tool for mitigating potential failures, particularly during the ramp-up phases of new products. However, its effectiveness is often limited by the reasoning capabilities of the FMEA tools, which are usually tabular structured. Meanwhile, large language models (LLMs) offer novel prospects for advanced natural language processing tasks. However, LLMs face challenges in tasks that require factual knowledge, a gap that retrieval-augmented generation (RAG) approaches aim to fill. RAG retrieves information from a non-parametric data store and uses a language model to generate responses. Building on this concept, we propose to enhance the non-parametric data store with a knowledge graph (KG). By integrating a KG into the RAG framework, we aim to leverage analytical and semantic question-answering capabilities for FMEA data. This paper contributes by presenting set-theoretic standardization and a schema for FMEA data, an algorithm for creating vector embeddings from the FMEA-KG, and a KG-enhanced RAG framework. Our approach is validated through a user experience design study, and we measure the precision and performance of the context retrieval recall. KW - FMEA KW - Risk assessment KW - Knowledge graph KW - Retrieval-augmented generation KW - Large language models ER - TY - BOOK TI - Künstliche Intelligenz selber programmieren für Dummies Junior : wer ist schlauer? Mensch oder Maschine AU - Schmid, Ute AU - Weitz, Katharina AU - Siebers, Michael PY - 2025 PB - Wiley-VCH GmbH CY - Weinheim ET - 2. vollständig überarbeitete und erweiterte Auflage SN - 978-3-527-72188-7 UR - https://fis.uni-bamberg.de/handle/uniba/107132 LA - deu ER - TY - JOUR TI - Project VoLL-KI : Learning from Learners AU - Kohlhase, Michael AU - Berges, Marc AU - Grubert, Jens AU - Landes, Dieter AU - Leidner, Jochen L. AU - Henrich, Andreas AU - Mittag, Florian AU - Nicklas, Daniela AU - Schmid, Ute AU - Sedlmaier, Yvonne AU - Ulbrich-vom Ende, Achim AU - Wolter, Diedrich PY - 2025 JO - Künstliche Intelligenz : KI ; Forschung, Entwicklung, Erfahrungen ; Organ des Fachbereichs 1 Künstliche Intelligenz der Gesellschaft für Informatik e.V., GI VL - 39 SP - 299–309 PB - Springer CY - Berlin ; Heidelberg SN - 0933-1875 DO - 10.1007/s13218-024-00846-9 UR - https://fis.uni-bamberg.de/handle/uniba/107128 LA - eng AB - “Learning from Learners” (“Von Lernenden Lernen”, “VoLL-KI ” for short) is a is collaborative research project with the goal of creating a practical toolbox of instruments at diferent levels of abstraction to improve the learning experience and outcomes for students of artifcial intelligence. Learning and teaching at tertiary education institutions are currently ITbased but not AI-supported. The VoLL-KI project aims to go this crucial next step. Using AI approaches (e.g., ML, symbolic AI, statistical AI), several educational technologies are developed on the diferent granularity of the study programs (e.g., course, semester, program). So, dashboards for study planning, recommender systems improving student advisory services and learning material selection, VR-based learning experiences, educational chatbots, and adaptive learning environments are developed. The systems are mostly deployed as prototypes KW - Computer-aided education KW - Intelligent tutoring systems KW - Teaching support for artifcial intelligence education KW - Computer-aided learning (CAL) KW - Data-driven learning quality management KW - Study course monitoring KW - Learning analytics ER - TY - CPAPER TI - SPECTRE : A Dataset for Spectral Reconstruction on Chip-Size Spectrometers with a Physics-Informed Augmentation Method AU - Wissing, Julio AU - Scholz, Teresa AU - Saloman, Stefan AU - Fargueta, Lidia AU - Junger, Stephan AU - Stefani, Alessio AU - Tschekalinskij, Wladimir AU - Scheele, Stephan AU - Schmid, Ute PY - 2024 T2 - IEEE SENSORS 2024 : Conference Proceedings SP - 1-4 PB - IEEE CY - [Piscataway, NJ] SN - 979-8-3503-6351-7 DO - 10.1109/sensors60989.2024.10784898 UR - https://fis.uni-bamberg.de/handle/uniba/114597 LA - eng ER - TY - CPAPER TI - FruitNeRF : A Unified Neural Radiance Field based Fruit Counting Framework AU - Meyer, Lukas AU - Gilson, Andreas AU - Schmid, Ute AU - Stamminger, Marc PY - 2024 T2 - 2024 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) SP - 1-8 PB - IEEE SN - 979-8-3503-7770-5 DO - 10.1109/iros58592.2024.10802065 UR - https://fis.uni-bamberg.de/handle/uniba/114015 LA - eng ER - TY - CHAP TI - Grundkompetenzen im Bereich Künstliche Intelligenz (AI Literacy) AU - Schmid, Ute Maria PY - 2024 T2 - Handbuch Lernen mit digitalen Medien : Wege der Transformation SP - 769-784 PB - Beltz CY - Weinheim ET - 3 SN - 978-3-407-83244-3 UR - https://fis.uni-bamberg.de/handle/uniba/112355 LA - deu ER - TY - CPAPER TI - Bayesian CAIPI : A Probabilistic Approach to Explanatory and Interactive Machine Learning AU - Slany, Emanuel AU - Scheele, Stephan AU - Schmid, Ute PY - 2024 T2 - Artificial Intelligence : ECAI 2023 International Workshops ; XAI^3, TACTIFUL, XI-ML, SEDAMI, RAAIT, AI4S, HYDRA, AI4AI ; Kraków, Poland, September 30 – October 4, 2023 ; Proceedings, Part 1 SP - 285-301 PB - Springer CY - Cham, Switzerland SN - 978-3-031-50395-5 DO - 10.1007/978-3-031-50396-2_16 UR - https://fis.uni-bamberg.de/handle/uniba/112331 LA - eng ER - TY - JOUR TI - Bildungskanon für eine digitale Gesellschaft : In der Schule müssen digitale Grundkompetenzen vermittelt werden AU - Schmid, Ute Maria PY - 2024 JO - Akademie aktuell : Zeitschrift der Bayerischen Akademie der Wissenschaften IS - 1 SP - 32-36 CY - München SN - 1436-753X UR - https://fis.uni-bamberg.de/handle/uniba/110903 LA - deu ER - TY - CPAPER TI - Explainable AI for Mixed Data Clustering AU - Amling, Jonas AU - Scheele, Stephan AU - Slany, Emanuel AU - Lang, Moritz AU - Schmid, Ute PY - 2024 T2 - Explainable Artificial Intelligence : Second World Conference, xAI 2024, Valletta, Malta, July 17–19, 2024, Proceedings SP - 42-62 PB - Springer CY - Cham T3 - Communications in Computer and Information Science (CCIS) SN - 978-3-031-63796-4 DO - 10.1007/978-3-031-63797-1_3 UR - https://fis.uni-bamberg.de/handle/uniba/107149 LA - eng ER - TY - CPAPER TI - Locally testing model detections for semantic global concepts AU - Motzkus, Frank Walter AU - Mikriukov, Georgii AU - Hellert, Christian AU - Schmid, Ute PY - 2024 T2 - Explainable artificial intelligence : second world conference, xAI 2024, Valletta, Malta, July 17-19, 2024 : proceedings SP - 137-159 PB - Springer CY - Cham SN - 978-3-031-63786-5 DO - 10.1007/978-3-031-63787-2_8 UR - https://fis.uni-bamberg.de/handle/uniba/107127 LA - eng ER - TY - CHAP TI - Trustworthy Artificial Intelligence : Comprehensible, Transparent and Correctable AU - Schmid, Ute PY - 2024 T2 - Introduction to digital humanism : a textbook SP - 151-164 PB - Springer CY - Cham SN - 978-3-031-45303-8 DO - 10.1007/978-3-031-45304-5_10 UR - https://fis.uni-bamberg.de/handle/uniba/107126 LA - eng AB - With the digital transformation, artificial intelligence (AI) applications are also finding their way into more and more areas of work and life. In particular, models learned from data are being used, which are mostly opaque black boxes. The fact that people can understand why an AI system behaves the way it does is necessary for various reasons: The model developers themselves must be able to assess properties of the learned models—in particular, possible biases due to overfitting to the data used for learning. For safety-critical applications, aspects of certification and testing are also becoming increasingly relevant. Domain experts— for example, in medical diagnostics or quality control in industrial production—must be able to comprehend, verify and, if necessary, correct system decisions. Consumers should understand why a system—a smart home control, a driving assistance—behaves in a certain way and why they are recommended certain products, offered certain tariffs or denied certain offers. After a brief introduction to the topic of AI, the chapter gives an overview of methods of the so-called third wave of AI. Central to this are approaches of explainable AI (XAI), which are intended to make the decisions of AI systems comprehensible. The main approaches are characterized and shown for which objectives and applications they are suitable in each case. It is shown that in addition to the highly regarded methods for visualization, methods that allow system decisions to be described in a differentiated manner are also particularly important. It is also argued that, in addition to comprehensibility, interactivity and correctability of AI systems are necessary so that AI systems do not restrict human competences but support them in partnership. ER - TY - JOUR TI - Explainable and interpretable machine learning and data mining AU - Atzmueller, Martin AU - Fürnkranz, Johannes AU - Kliegr, Tomáš AU - Schmid, Ute PY - 2024 JO - Data mining and knowledge discovery VL - 38 IS - 5 SP - 2571-2595 PB - Springer Science + Business Media B.V CY - Dordrecht [u.a.] SN - 1384-5810 DO - 10.1007/s10618-024-01041-y UR - https://fis.uni-bamberg.de/handle/uniba/107125 LA - eng AB - The growing number of applications of machine learning and data mining in many domains—from agriculture to business, education, industrial manufacturing, and medicine—gave rise to new requirements for how to inspect and control the learned models. The research domain of explainable artifcial intelligence (XAI) has been newly established with a strong focus on methods being applied post-hoc on blackbox models. As an alternative, the use of interpretable machine learning methods has been considered—where the learned models are white-box ones. Black-box models can be characterized as representing implicit knowledge—typically resulting from statistical and neural approaches of machine learning, while white-box models are explicit representations of knowledge—typically resulting from rule-learning approaches. In this introduction to the special issue on ‘Explainable and Interpretable Machine Learning and Data Mining’ we propose to bring together both perspectives, pointing out commonalities and discussing possibilities to integrate them. KW - Explainable AI KW - Explainable and interpretable machine learning KW - Explainable and interpretable data mining KW - Hybrid artifcial intelligence ER - TY - CPAPER TI - Near Hit and Near Miss Example Explanations for Model Revision in Binary Image Classification AU - Finzel, Bettina AU - Knoblach, Judith AU - Thaler, Anna Magdalena AU - Schmid, Ute PY - 2024 T2 - Intelligent Data Engineering and Automated Learning – IDEAL 2024 : 25th International Conference, Valencia, Spain, November 20–22, 2024, Proceedings, Part II SP - 260-271 PB - Springer Nature Switzerland CY - Cham SN - 9783031777370 DO - 10.1007/978-3-031-77738-7_22 UR - https://fis.uni-bamberg.de/handle/uniba/106515 LA - eng ER - TY - GEN TI - When a Relation Tells More Than a Concept : Exploring and Evaluating Classifier Decisions with CoReX AU - Finzel, Bettina AU - Hilme, Patrick AU - Rabold, Johannes AU - Schmid, Ute PY - 2024 SP - 1-56 PB - arXiv DO - 10.48550/arxiv.2405.01661 UR - https://fis.uni-bamberg.de/handle/uniba/106516 LA - eng ER - TY - CPAPER TI - Explaining with Attribute-Based and Relational Near Misses : An Interpretable Approach to Distinguishing Facial Expressions of Pain and Disgust AU - Finzel, Bettina AU - Kuhn, Simon P. AU - Tafler, David E. AU - Schmid, Ute Maria PY - 2024 T2 - Inductive Logic Programming : 31st International Conference, ILP 2022, Windsor Great Park, UK, September 28–30, 2022, Proceedings SP - 40-51 PB - Springer Nature Switzerland CY - Cham SN - 9783031556296 DO - 10.1007/978-3-031-55630-2_4 UR - https://fis.uni-bamberg.de/handle/uniba/106518 LA - eng ER - TY - CHAP TI - Informatische Grundbildung in der Grundschule : Kombinierter Einsatz von haptischen Spiel- und Erfahrungsmaterialien mit digitalen Übungen AU - Gärtig-Daugs, Anja AU - Schmid, Ute PY - 2024 T2 - Digitales Lernen in der Grundschule IV : Fachdidaktische Perspektiven auf den Einsatz digitaler Werkzeuge SP - 104-124 PB - Waxmann CY - Münster ET - 1 SN - 978-3-8309-4927-5 UR - https://fis.uni-bamberg.de/handle/uniba/104712 LA - deu ER - TY - BOOK TI - Künstliche Intelligenz für Lehrkräfte : eine fachliche Einführung mit didaktischen Hinweisen ED - Furbach, Ulrich ED - Kitzelmann, Emanuel ED - Michaeli, Tilman ED - Schmid, Ute PY - 2024 PB - Springer Fachmedien Wiesbaden CY - Wiesbaden T3 - ars digitalis ET - 1 SN - 978-3-658-44247-7 DO - 10.1007/978-3-658-44248-4 UR - https://fis.uni-bamberg.de/handle/uniba/98231 LA - deu ER - TY - BOOK TI - Künstliche Intelligenz selber programmieren für Dummies Junior AU - Schmid, Ute AU - Weitz, Katharina AU - Siebers, Michael PY - 2024 PB - Wiley-VCH CY - Weinheim ET - 2 SN - 978-3-527-84752-5 UR - https://fis.uni-bamberg.de/handle/uniba/97963 LA - deu ER - TY - JOUR TI - BAMFORESTS : Bamberg Benchmark Forest Dataset of Individual Tree Crowns in Very-High-Resolution UAV Images AU - Troles, Jonas AU - Schmid, Ute AU - Fan, Wen AU - Tian, Jiaojiao PY - 2024 JO - Remote Sensing for Forest Morphological and Physiological Traits Monitoring VL - 16 IS - 11 SP - 1-12 PB - MDPI AG CY - Basel SN - 2072-4292 DO - 10.3390/rs16111935 UR - https://fis.uni-bamberg.de/handle/uniba/95423 LA - eng AB - The anthropogenic climate crisis results in the gradual loss of tree species in locations where they were previously able to grow. This leads to increasing workloads and requirements for foresters and arborists as they are forced to restructure their forests and city parks. The advancements in computer vision (CV)—especially in supervised deep learning (DL)—can help cope with these new tasks. However, they rely on large, carefully annotated datasets to produce good and generalizable models. This paper presents BAMFORESTS: a dataset with 27,160 individually delineated tree crowns in 105 ha of very-high-resolution UAV imagery gathered with two different sensors from two drones. BAMFORESTS covers four areas of coniferous, mixed, and deciduous forests and city parks. The labels contain instance segmentations of individual trees, and the proposed splits are balanced by tree species and vitality. Furthermore, the dataset contains the corrected digital surface model (DSM), representing tree heights. BAMFORESTS is annotated in the COCO format and is especially suited for training deep neural networks (DNNs) to solve instance segmentation tasks. BAMFORESTS was created in the BaKIM project and is freely available under the CC BY 4.0 license. KW - benchmark dataset KW - individual tree crown KW - instance segmentation KW - UAV imagery KW - tree species KW - forest ER - TY - CPAPER TI - Domain-Specific Evaluation of Visual Explanations for Application-Grounded Facial Expression Recognition AU - Finzel, Bettina AU - Rieger, Ines AU - Kuhn, Simon AU - Schmid, Ute PY - 2024 SP - 31-44 PB - Otto-Friedrich-Universität CY - Bamberg UR - https://fis.uni-bamberg.de/handle/uniba/95294 LA - eng AB - Research in the field of explainable artificial intelligence has produced a vast amount of visual explanation methods for deep learning-based image classification in various domains of application. However, there is still a lack of domain-specific evaluation methods to assess an explanation’s quality and a classifier’s performance with respect to domain-specific requirements. In particular, evaluation methods could benefit from integrating human expertise into quality criteria and metrics. Such domain-specific evaluation methods can help to assess the robustness of deep learning models more precisely. In this paper, we present an approach for domain-specific evaluation of visual explanation methods in order to enhance the transparency of deep learning models and estimate their robustness accordingly. As an example use case, we apply our framework to facial expression recognition. We can show that the domain-specific evaluation is especially beneficial for challenging use cases such as facial expression recognition and provides application-grounded quality criteria that are not covered by standard evaluation methods. Our comparison of the domain-specific evaluation method with standard approaches thus shows that the quality of the expert knowledge is of great importance for assessing a model’s performance precisely. KW - Application-Grounded Facial Expression Recognition ER - TY - GEN TI - Comprehensible Artificial Intelligence on Knowledge Graphs : A survey AU - Schramm, Simon AU - Wehner, Christoph AU - Schmid, Ute PY - 2024 SP - 1-23 PB - arXiv DO - 10.48550/arxiv.2404.03499 UR - https://fis.uni-bamberg.de/handle/uniba/95002 LA - eng AB - Artificial Intelligence applications gradually move outside the safe walls of research labs and invade our daily lives. This is also true for Machine Learning methods on Knowledge Graphs, which has led to a steady increase in their application since the beginning of the 21st century. However, in many applications, users require an explanation of the Artificial Intelligences decision. This led to increased demand for Comprehensible Artificial Intelligence. Knowledge Graphs epitomize fertile soil for Comprehensible Artificial Intelligence, due to their ability to display connected data, i.e. knowledge, in a human- as well as machine-readable way. This survey gives a short history to Comprehensible Artificial Intelligence on Knowledge Graphs. Furthermore, we contribute by arguing that the concept Explainable Artificial Intelligence is overloaded and overlapping with Interpretable Machine Learning. By introducing the parent concept Comprehensible Artificial Intelligence, we provide a clear-cut distinction of both concepts while accounting for their similarities. Thus, we provide in this survey a case for Comprehensible Artificial Intelligence on Knowledge Graphs consisting of Interpretable Machine Learning on Knowledge Graphs and Explainable Artificial Intelligence on Knowledge Graphs. This leads to the introduction of a novel taxonomy for Comprehensible Artificial Intelligence on Knowledge Graphs. In addition, a comprehensive overview of the research on Comprehensible Artificial Intelligence on Knowledge Graphs is presented and put into the context of the taxonomy. Finally, research gaps in the field of Comprehensible Artificial Intelligence on Knowledge Graphs are identified for future research. KW - Comprehensible Artificial Intelligence ER - TY - THES TI - Erwerb rekursiver Programmiertechniken als Induktion von Konzepten und Regeln : ein kognitionswissenschaftlicher Zugang zum Erwerb kognitiver Fertigkeiten AU - Schmid, Ute PY - 2024 PB - Otto-Friedrich-Universität CY - Bamberg DO - 10.20378/irb-90968 UR - https://fis.uni-bamberg.de/handle/uniba/90968 LA - deu AB - - KW - - ER - TY - CPAPER TI - Erwerb rekursiver Programmiertechniken als Induktion von Konzepten und Regeln AU - Schmid, Ute AU - Kaup, Barbara PY - 2024 SP - 418-419 PB - Otto-Friedrich-Universität CY - Bamberg DO - 10.20378/irb-90971 UR - https://fis.uni-bamberg.de/handle/uniba/90971 LA - deu AB - - KW - Studie ER - TY - JOUR TI - Programmieren lernen : Unterstützung des Erwerbs rekursiver Programmiertechniken durch Beispielfunktionen und Erklärungstexte AU - Schmid, Ute PY - 2024 SP - 47-54 PB - Otto-Friedrich-Universität CY - Bamberg DO - 10.20378/irb-90973 UR - https://fis.uni-bamberg.de/handle/uniba/90973 LA - deu AB - Beim Erwerb von Programmiertechniken ist das Lernen rekursiver Kontrollstrukturen für Anfänger meist die größte Hürde. Die Auswahl von geeignetem Lehrmaterial zur Unterstütznng des Lernprozesses ist deshalb gerade für die Vermittlung rekursiver Programmierung relevant. Es wird eine Studie vorgestellt, in der der Einfluß von zwei Lehrmaterialien - Beispielprogrammen und erklärenden Texten - auf den Erwerb rekursiver Programmiertechniken untersucht wurde. Es zeigte sich, daß Lernen mit Erklärungen und mit Beispielen zu vergleichbaren Transferleistungen führt, die Performanz während des Lernprozesses ist bei Unterstützung durch Erklärungen allerdings wesentlich besser als bei Unterstützung durch Beispiele. KW - Wissenserwerb ER - TY - BOOK TI - Induktion von Perspektive in räumlichen Situationsmodellen in Abhängigkeit vom sprachlichen Ausdruck AU - Fricke, Ellen AU - Durstewitz, Daniel AU - Claus, Berry AU - Schmid, Ute PY - 2024 PB - Otto-Friedrich-Universität CY - Bamberg DO - 10.20378/irb-91267 UR - https://fis.uni-bamberg.de/handle/uniba/91267 LA - deu AB - Es werden zwei Untersuchungen vorgestellt, die auf einer Serie von Experimenten von Franklin, Tversky, Bryant u.a. aufbauen. In diesen Experimenten wurde gezeigt, daß Leser in aufgrund textueller Beschreibungen aufgebauter räumlicher Situationsmodelle unterschiedliche Perspektiven einnehmen, die sich anhand der Verfügbarkeitsmuster von Objekten aus dem Raum differenzieren lassen. Unser Anliegen war es, zu untersuchen, inwieweit die in den Raumbeschreibungen verwendeten deiktischen Lokalisierungsausdrücke und unterschiedliche verbale Ausdrücke bestimmte Perspektiven induzieren, und ob sich unterschiedliche induzierte Perspektiven zur semantischen Differenzierung von Ausdrücken mit Wahrnehmungsverben heranziehen lassen. Unser Textmaterial bestand aus kurzen Geschichten, in denen ein handelnder Protagonist in einem Raum beschrieben wurde. Die Position verschiedener Objekte wurde entweder relativ zum Protagonisten (z.B. "rechts von ... ") oder relativ zur virtuellen Perspektive eines Erzählers (z.B. "An der rechten Wand ... ") festgelegt. In nachfolgenden Sätzen wurden aktive Handlungen des Protagonisten oder passive Wahrnehmungen mit Ausdrücken wie "Er sieht zum...", "Er geht zum ... ", "Er sieht den... " oder "Dort ist ... " beschrieben. Zwar zeigen die Ergebnisse signifikante Unterschiede in den Verfügbarkeitsmustem in Abhängigkeit von der Raumbeschreibung und den verwendeten verbalen Ausdrücken, die auch darauf hindeuten, daß sich semantische Aspekte von Ausdrücken mit Wahrnehmungs- und Handlungsverben unterscheiden lassen, jedoch sind sie inkonsistent zu den von Franklin, Tversky u.a. gefundenen und sind nur schwer interpretierbar. Aus den Reaktionszeitmustern konnte die eingenommene Perspektive nicht eindeutig und konsistent mit verschiedenen theoretischen Vorstellungen ermittelt werden. KW - - ER - TY - CPAPER TI - Worked Examples as Application of Analogical Reasoning in Intelligent Tutoring and their Effects on SQL Competencies AU - Thaler, Anna Magdalena AU - Mitrovic, Antonija AU - Schmid, Ute PY - 2024 SP - 157-158 PB - Otto-Friedrich-Universität CY - Bamberg UR - https://fis.uni-bamberg.de/handle/uniba/94793 LA - eng AB - - KW - Intelligent Tutoring KW - SQL Competencies ER - TY - BOOK TI - Der Einfluß von Beispielähnlichkeit auf induktive Lernprozesse beim rekursiven Programmieren AU - Schmid, Ute AU - Kaup, Barbara PY - 2024 PB - Otto-Friedrich-Universität CY - Bamberg DO - 10.20378/irb-90967 UR - https://fis.uni-bamberg.de/handle/uniba/90967 LA - deu AB - Es wurde eine Untersuchung durchgeführt, bei der geprüft wurde, auf welche Weise der induktive Erwerb von rekursiven Programmiertechniken durch die Ähnlichkeit von Beispiel- und Zielproblem beeinflußt wird. Dabei wurde davon ausgegangen, daß die Art der Beispiele sowohl den Lösungserfolg rekursiver Aufgaben als auch das induzierte Wissen über den neuen Problembereich beeinflussen. Die Beispielähnlichkeit wurde systematisch variiert. Zusätzlich wurde die Wirkung von Vergleichs- und Anpassungsprozessen getrennt erfaßt, indem einer Gruppe von Probanden das Ergebnis des Vergleichsprozesses vorgegeben wurde. 55 Programmieranfänger nahmen an vier aufeinanderfolgenden Tagen jeweils 3 Stunden an der Untersuchung teil. Nach Vermittlung der Syntax einer einfachen funktionalen Sprache, sollten die Probanden am dritten und vierten Tag sechs rekursive Funktionen am Rechner programmieren. Dabei wurde ihnen je ein Beispiel, entsprechend der experimentellen Bedingungen vorgegeben. Geprüft wurde der Einfluß der Lernbedingung auf (1) den Prozeß der Aufgabenlösungen und (2) den resultierenden Wissenserwerb. Der Wissenserwerb wurde dabei zum einen durch einen Abschlußtest erfaßt, bei dem verschiedene Transferaufgaben zu lösen waren. Zum anderen wurde die Schemainduktion explizit erfaßt, indem die Probanden zu drei Zeitpunkten jeweils 28 Funktionen sortieren sollten. Es zeigte sich, daß die Lernbedingung einen bedeutsamen Einfluß auf die Aufgabenlösung hat: Je ähnlicher ein Beispiel zum Zielproblem ist, desto wahrscheinlicher wird die Aufgabe gelöst; die Vorgabe des Vergleichsprozesses führt ebenfalls zu einer erhöhten Lösungswahrscheinlichkeit. Bezüglich des Wissenserwerbs zeigt die Lernbedingung keinen eindeutigen Einfluß. Betrachtet man die Merkmale, nach denen die Probanden sortieren, zeigt sich, daß Probanden, die das Merkmal "Rekursionstyp" zur Klassifikation verwenden, sowohl mehr Aufgaben lösen als auch eine höhere Transferleistung im Abschlußtest zeigen. KW - - ER - TY - BOOK TI - Zum Einfluß von Situationsmodellen auf die Verarbeitung konsistenter versus inkonsistenter Textinformation AU - Durstewitz, Daniel AU - Schmid, Ute AU - Claus, Berry AU - Eyferth, Klaus PY - 2024 PB - Otto-Friedrich-Universität CY - Bamberg T3 - KIT-Report / Institut für Software und Theoretische Informatik, Fachbereich 20, Technische Universität Berlin / Projektgruppe KIT, Künstliche Intelligenz und Textverstehen DO - 10.20378/irb-92878 UR - https://fis.uni-bamberg.de/handle/uniba/92878 LA - deu AB - Die vorliegende Untersuchung beschäftigt sich mit der Rolle von Situationsmodellen beim Textverstehen. Unter Situationsmodellen werden allgemein analoge, bisweilen bildhaft-visuelle, Repräsentationen verstanden, die räumliche und funktionale Beziehungen homomorph zu natürlichen Situationen abbilden. Situationsmodellen wird eine entscheidende Rolle bei der Interpretation von Sätzen in Textzusammenhängen, insbesondere bei der Zuweisung von Referenzobjekten zu Ausdrücken (z.B. in der Anaphernresolution), zugesprochen. In Anlehnung an Glenberg, Meyer & Lindem (1987) soll diese Studie die Rolle von Situationsmodellen beim Textverstehen weiter klären. Dazu wurde in kurzen Geschichten, bestehend aus jeweils fünf Sätzen, ein Zielobjekt (Target) entweder mit anderen Objekten oder Agenten im aktuellen Situationsmodell räumlich verbunden ('assoziiert') oder von diesen getrennt ('dissoziiert'). Der letzte (kritische) Satz jeder Geschichte war dann jeweils konsistent oder inkonsistent mit der Lokation des Targets. Erhoben wurden Lesezeiten für den letzten Satz sowie Fehlerraten und Reaktionszeiten bei der Beantwortung eines Behauptungssatzes, der jeder Geschichte folgte. Unsere Hypothese ist, daß unter der Bedingung 'assoziiert' die Lesezeiten für konsistente Sätze kürzer ausfallen als für inkonsistente, daß sich diese Differenz unter der Bedingung 'dissoziiert' aber nicht findet, und begründen dies folgendermaßen: Hängt das Verstehen des kritischen Satzes vom jeweils aktuellen Situationsmodell ab, so führt eine inkonsistente Aussage über die Lokation des Targets nur dann zu Interpretationsschwierigkeiten, wenn dieses auch im Situationsmodell repräsentiert ist. Falls dies, wie für die dissoziierte Bedingung angenommen, nicht mehr der Fall ist, sollten auch inkonsistente Informationen keine Verständnisprobleme bereiten. Unsere Befunde stützen in der Tendenz die Hypothese, jedoch nur für einige der Geschichten. Für diese sind die Unterschiede in den Lesezeiten unter der assoziierten Bedingung größer als unter der dissoziierten. Wegen erheblicher Varianz zwischen den Geschichten wurde das Ergebnis nicht signifikant. Eine Analyse der Fehlerraten ließ einen Haupteffekt des Faktors Konsistenz erkennen: Nach inkonsistenten Schlußsätzen kommt es häufiger zur Fehllokalisierung assoziierter und dissoziierter Objekte. Weitere Untersuchungen, in denen die Konstruktion der Geschichten strengeren Kriterien folgt, damit eindeutigere Schlußfolgerungn möglich sind, sollen folgen. KW - - ER - TY - BOOK TI - A method for analyzing computer users' behavior sequences AU - Schmid, Ute AU - Konerding, Uwe PY - 2024 PB - Otto-Friedrich-Universität CY - Bamberg DO - 10.20378/irb-92881 UR - https://fis.uni-bamberg.de/handle/uniba/92881 LA - eng AB - This paper presents a formal approach to analyzing behavioral sequences produced by computer users. Following this approach, the behavioral sequences are represented as square transition matrices, distances between the individual matrices are calculated, and the resulting distance matrix is scaled multidimensionally. The emerging scales reflect differences in the users' problem solving behavior and can be used as a guideline for detecting behavioral aspects influencing quality of task solution. The method was exemplarily applied to two different kinds of behavioral data, the first reported by Upmeyer, Meseke & Enzmann (1988) and the second by Eyferth, Widowski & Schmid (1991). KW - cornputer user KW - behavior sequences KW - multidimensional scaling ER - TY - BOOK TI - Determinanten des Erwerbs von Programmierkompetenz AU - Schmid, Ute AU - Ulber, Daniela PY - 2024 PB - Otto-Friedrich-Universität CY - Bamberg DO - 10.20378/irb-93222 UR - https://fis.uni-bamberg.de/handle/uniba/93222 LA - deu AB - Es wird eine empirische Untersuchung vorgestellt, bei der der Einfluß von 1) der Art der vorgegebenen Lernhilfe und 2) dem kognitiven Stil von Personen auf das Lösen von rekursiven Programmieraufgaben und den Lerntransfer geprüft wird. Als Lernhilfen werden dabei erklärende Texte, Beispielprogramme oder beide genannten Materialien verwendet. Zudem wurden die untersuchten Personen aufgrund der Differenz zweier Testskalen als induktive und deduktive Denker klassifiziert. Es zeigte sich, daß - abweichend von den formulierten Hypothesen - die Aufgabenlösungen besser durch Erklärungen als durch Beispiele unterstützt werden. Dieser Unterschied resultiert jedoch nicht in Unterschieden bezüglich dem Lerntransfer. Bezüglich des Einflusses der Denkstile ergab sich ebenfalls ein nicht den Hypothesen entsprechendes Ergebnis: Personen mit induktivem Denkstil kommen besser mit Erklärungen, Personen mit deduktivem Stil besser mit Beispielen zurecht. Um genauere Hinweise über den Einfluß verschiedener Lernhilfen auf Aufgabenlösung und Lerntransfer zu erhalten, werden zusätzlich verschiedene Kennwerte zur Erfassung des Hilfeaufrufverhaltens betrachtet. KW - - ER - TY - BOOK TI - Der Einfluß von Lehrmaterial auf das Lösen rekursiver Programmieraufgaben : eine Fehleranalyse AU - Schmid, Ute AU - Gräbener, Jens PY - 2024 PB - Otto-Friedrich-Universität CY - Bamberg DO - 10.20378/irb-93220 UR - https://fis.uni-bamberg.de/handle/uniba/93220 LA - deu AB - In einer Untersuchung zum Erwerb rekursiver Programmiertechniken (Schmid & Ulber 1993) wurde der Einfluß von Lehrmaterialien 1) auf den Lösungserfolg bei Programmieraufgaben und 2) auf den Lerntransfer geprüft. Als Lehrmaterialien wurden dabei 1) erklärende Texte zu den Aufgaben, 2) Beispielfunktionen und 3) beide Materialien verwendet. Es zeigte sich, daß alle drei Lernbedingungen zu vergleichbarem Lerntransfer führen. Bezüglich des Lösungserfolges bei den Programmieraufgaben ergibt sich jedoch ein bedeutsamer Nachteil für die Probanden, die nur Beispielfunktionen zur Verfügung haben. Um genaueren Aufschluß über die Wirkung von Beispielfunktionen auf das Lösen von Aufgaben zu erhalten, wurde einer Fehleranalyse durchgeführt. Dabei wird deutlich, daß Programmieranfänger noch keine adäquaten Regeln zur Verfügung haben, um Beispielfunktionen auf Aufgaben zu übertragen: Es werden häufig gerade die Anteile der Beispiele übernommen, die an die Aufgabe hätten angepaßt werden müssen, gleichbleibende Teile werden dagegen nicht als solche erkannt. Dieses Vorgehen führt zu einem hohen Anteil an semantischen Fehlern, vor allem zu nicht-terminierenden Lösungen. Dagegen produzieren Probanden, die nur mit erklärenden Texten oder beiden Materialien arbeiten häufig schnell semantisch korrekte Lösungen, die allerdings syntaktische Fehler enthalten. Lediglich die vor allem von der Beispielgruppe erzeugten Fehler stehen jedoch in einem Zusammenhang mit dem Lösungserfolg bei den Aufgaben. KW - - ER - TY - JOUR TI - Explaining and Evaluating Deep Tissue Classification by Visualizing Activations of Most Relevant Intermediate Layers AU - Mohammed, Aliya AU - Geppert, Carol AU - Hartmann, Arnd AU - Kuritcyn, Petr AU - Bruns, Volker AU - Schmid, Ute AU - Wittenberg, Thomas AU - Benz, Michaela AU - Finzel, Bettina PY - 2024 SP - 229-232 PB - Otto-Friedrich-Universität CY - Bamberg UR - https://fis.uni-bamberg.de/handle/uniba/93007 LA - eng AB - Deep Learning-based tissue classification may support pathologists in analyzing digitized whole slide images. However, in such critical tasks, only approaches that can be validated by medical experts in advance to deployment, are suitable. We present an approach that contributes to making automated tissue classification more transparent. We step beyond broadly used visualizations for last layers of a convolutional neural network by identifying most relevant intermediate layers applying Grad-CAM. A visual evaluation by a pathologist shows that these layers assign relevance, where important morphological structures are present in case of correct class decisions. We introduce a tool that can be easily used by medical experts for such validation purposes for any convolutional neural network and any layer. Visual explanations for intermediate layers provide insights into a neural network’s decision for histopathological tissue classification. In future research also the context of the input data must be considered. KW - Digital Pathology KW - Deep Learning KW - XAI KW - Evaluation KW - Grad-CAM KW - Intelligent user interface ER - TY - CHAP TI - ChatGPT im Kontext der frühkindlichen Bildung AU - Schmid, Ute Maria PY - 2023 T2 - Das Kita- Handbuch PB - Herder Verlag UR - https://fis.uni-bamberg.de/handle/uniba/112389 LA - deu ER - TY - CPAPER TI - Inductive Logic Programming for Explainable Graph Clustering AU - Schramm, Simon AU - Schmid, Ute PY - 2023 T2 - Proceedings : IEEE International Conference on Knowledge Graph ; 1–2 December 2023, Shanghai, China SP - 235-242 PB - IEEE Computer Society, Conference Publishing Services (CPS) CY - Los Alamitos, California ; Washington ; Tokyo SN - 979-8-3503-0709-2 DO - 10.1109/ickg59574.2023.00034 UR - https://fis.uni-bamberg.de/handle/uniba/112373 LA - eng ER - TY - CPAPER TI - Cluster Robust Inference for Embedding-Based Knowledge Graph Completion AU - Schramm, Simon AU - Niklas, Ulrich AU - Schmid, Ute PY - 2023 T2 - Knowledge Science, Engineering and Management : 16th International Conference, KSEM 2023, Guangzhou, China, August 16–18, 2023 ; Proceedings, Part I SP - 284-299 PB - Springer CY - Cham, Switzerland T3 - Lecture Notes in Computer Science SN - 978-3-031-40282-1 DO - 10.1007/978-3-031-40283-8_25 UR - https://fis.uni-bamberg.de/handle/uniba/112371 LA - eng ER - TY - JOUR TI - Explanatory machine learning for sequential human teaching AU - Ai, Lun AU - Langer, Johannes AU - Muggleton, Stephen H. AU - Schmid, Ute PY - 2023 SP - 3591-3632 PB - Otto-Friedrich-Universität CY - Bamberg UR - https://fis.uni-bamberg.de/handle/uniba/108497 LA - eng AB - The topic of comprehensibility of machine-learned theories has recently drawn increasing attention. Inductive logic programming uses logic programming to derive logic theories from small data based on abduction and induction techniques. Learned theories are represented in the form of rules as declarative descriptions of obtained knowledge. In earlier work, the authors provided the first evidence of a measurable increase in human comprehension based on machine-learned logic rules for simple classification tasks. In a later study, it was found that the presentation of machine-learned explanations to humans can produce both beneficial and harmful effects in the context of game learning. We continue our investigation of comprehensibility by examining the effects of the ordering of concept presentations on human comprehension. In this work, we examine the explanatory effects of curriculum order and the presence of machine-learned explanations for sequential problem-solving. We show that (1) there exist tasks A and B such that learning A before learning B results in better comprehension for humans in comparison to learning B before learning A and (2) there exist tasks A and B such that the presence of explanations when learning A contributes to improved human comprehension when subsequently learning B. We propose a framework for the effects of sequential teaching on comprehension based on an existing definition of comprehensibility and provide evidence for support from data collected in human trials. Our empirical study involves curricula that teach novices the merge sort algorithm. Our results show that sequential teaching of concepts with increasing complexity (a) has a beneficial effect on human comprehension and (b) leads to human re-discovery of divide-and-conquer problem-solving strategies, and (c) allows adaptations of human problem-solving strategy with better performance when machine-learned explanations are also presented. KW - Explainable artificial intelligence KW - Machine learning comprehensibility KW - Meta-interpretive learning KW - Inductive logic programming ER - TY - JOUR TI - Toward human-level concept learning : Pattern benchmarking for AI algorithms AU - Holzinger, Andreas AU - Saranti, Anna AU - Angerschmid, Alessa AU - Finzel, Bettina AU - Schmid, Ute AU - Mueller, Heimo PY - 2023 JO - Patterns VL - 4 IS - 8 SP - 1-21 PB - Elsevier CY - Amsterdam SN - 2666-3899 DO - 10.1016/j.patter.2023.100788 UR - https://fis.uni-bamberg.de/handle/uniba/106517 LA - eng AB - Artificial intelligence (AI) today is very successful at standard pattern-recognition tasks due to the availability of large amounts of data and advances in statistical data-driven machine learning. However, there is still a large gap between AI pattern recognition and human-level concept learning. Humans can learn amazingly well even under uncertainty from just a few examples and are capable of generalizing these concepts to solve new conceptual problems. The growing interest in explainable machine intelligence requires experimental environments and diagnostic/benchmark datasets to analyze existing approaches and drive progress in pattern analysis and machine intelligence. In this paper, we provide an overview of current AI solutions for benchmarking concept learning, reasoning, and generalization; discuss the state-of-the-art of existing diagnostic/ benchmark datasets (such as CLEVR, CLEVRER, CLOSURE, CURI, Bongard-LOGO, V-PROM, RAVEN, Kandinsky Patterns, CLEVR-Humans, CLEVRER-Humans, and their extension containing human language); and provide an outlook of some future research directions in this exciting research domain. ER - TY - CPAPER TI - Perzeptrons programmieren und explorieren im Rahmen der Open Roberta Lernumgebung AU - Münsterberg, Alisa Veronique AU - Budde, Reinhard AU - Leimbach, Thorsten AU - Schmid, Ute PY - 2023 T2 - Informatikunterricht zwischen Aktualität und Zeitlosigkeit : 20.-22.09.2023, Würzburg, Deutschland SP - 435-436 PB - Gesellschaft für Informatik e.V. CY - Bonn SN - 978-3-88579-730-2 DO - 10.18420/infos2023-056 UR - https://fis.uni-bamberg.de/handle/uniba/95305 LA - deu AB - Die Lowcode Robotics Platform OpenRoberta Lab wurde um Bausteine zur Programmierung von Perzeptronen erweitert. Damit wird die Möglichkeit geschaffen, dass Kinder dieGrundprinzipien des maschinellen Lernens als Generalisierung über Beispiele direkt umsetzen und interaktiv explorieren können. KW - Programmierplattform; KW - Maschinelles Lernen KW - Interaktives Lernen ER - TY - JOUR TI - Comprehensible Artificial Intelligence on Knowledge Graphs : A survey AU - Schramm, Simon Gerhard AU - Wehner, Christoph AU - Schmid, Ute PY - 2023 JO - Web semantics : science, services and agents on the World Wide Web VL - 79 IS - December 2023, 100806 SP - 1-17 PB - Elsevier CY - Amsterdam [u.a.] SN - 1570-8268 DO - 10.1016/j.websem.2023.100806 UR - https://fis.uni-bamberg.de/handle/uniba/95045 LA - eng ER - TY - CPAPER TI - Task Planning Support for Arborists and Foresters : Comparing Deep Learning Approaches for Tree Inventory and Tree Vitality Assessment Based on UAV-Data AU - Troles, Jonas AU - Nieding, Richard AU - Simons, Sonia AU - Schmid, Ute PY - 2023 T2 - Innovations for Community Services : 23rd International Conference, I4CS 2023, Bamberg, Germany, September 11–13, 2023 ; Proceedings SP - 103-122 PB - Springer Nature Switzerland CY - Cham SN - 978-3-031-40851-9 DO - 10.1007/978-3-031-40852-6_6 UR - https://fis.uni-bamberg.de/handle/uniba/95001 LA - eng ER - TY - JOUR TI - Explanatory machine learning for sequential human teaching AU - Ai, Lun AU - Langer, Johannes AU - Muggleton, Stephen H. AU - Schmid, Ute PY - 2023 JO - Machine learning VL - 112 IS - 10 SP - 3591-3632 PB - Springer CY - Dordrecht [u.a.] SN - 0885-6125 DO - 10.1007/s10994-023-06351-8 UR - https://fis.uni-bamberg.de/handle/uniba/94999 LA - eng AB - The topic of comprehensibility of machine-learned theories has recently drawn increasing attention. Inductive logic programming uses logic programming to derive logic theories from small data based on abduction and induction techniques. Learned theories are represented in the form of rules as declarative descriptions of obtained knowledge. In earlier work, the authors provided the first evidence of a measurable increase in human comprehension based on machine-learned logic rules for simple classification tasks. In a later study, it was found that the presentation of machine-learned explanations to humans can produce both beneficial and harmful effects in the context of game learning. We continue our investigation of comprehensibility by examining the effects of the ordering of concept presentations on human comprehension. In this work, we examine the explanatory effects of curriculum order and the presence of machine-learned explanations for sequential problem-solving. We show that (1) there exist tasks A and B such that learning A before learning B results in better comprehension for humans in comparison to learning B before learning A and (2) there exist tasks A and B such that the presence of explanations when learning A contributes to improved human comprehension when subsequently learning B. We propose a framework for the effects of sequential teaching on comprehension based on an existing definition of comprehensibility and provide evidence for support from data collected in human trials. Our empirical study involves curricula that teach novices the merge sort algorithm. Our results show that sequential teaching of concepts with increasing complexity (a) has a beneficial effect on human comprehension and (b) leads to human re-discovery of divide-and-conquer problem-solving strategies, and (c) allows adaptations of human problem-solving strategy with better performance when machine-learned explanations are also presented. KW - Explainable artificial intelligence KW - Machine learning comprehensibility KW - Meta-interpretive learning KW - Inductive logic programming ER - TY - JOUR TI - FairCaipi : A Combination of Explanatory Interactive and Fair Machine Learning for Human and Machine Bias Reduction AU - Heidrich, Louisa AU - Slany, Emanuel AU - Scheele, Stephan AU - Schmid, Ute PY - 2023 JO - Machine learning and knowledge extraction VL - 5 IS - 4 SP - 1519-1538 PB - MDPI CY - Basel SN - 2504-4990 DO - 10.3390/make5040076 UR - https://fis.uni-bamberg.de/handle/uniba/94998 LA - eng AB - The rise of machine-learning applications in domains with critical end-user impact has led to a growing concern about the fairness of learned models, with the goal of avoiding biases that negatively impact specific demographic groups. Most existing bias-mitigation strategies adapt the importance of data instances during pre-processing. Since fairness is a contextual concept, we advocate for an interactive machine-learning approach that enables users to provide iterative feedback for model adaptation. Specifically, we propose to adapt the explanatory interactive machine-learning approach Caipi for fair machine learning. FairCaipi incorporates human feedback in the loop on predictions and explanations to improve the fairness of the model. Experimental results demonstrate that FairCaipi outperforms a state-of-the-art pre-processing bias mitigation strategy in terms of the fairness and the predictive performance of the resulting machine-learning model. We show that FairCaipi can both uncover and reduce bias in machine-learning models and allows us to detect human bias. KW - fair machine learning KW - explanatory and interactive machine learning ER - TY - CPAPER TI - Domain-Specific Evaluation of Visual Explanations for Application-Grounded Facial Expression Recognition AU - Finzel, Bettina AU - Rieger, Ines AU - Kuhn, Simon AU - Schmid, Ute Maria PY - 2023 T2 - Machine learning and knowledge extraction : 7th IFIP TC 5, TC 12, WG 8.4, WG 8.9, WG 12.9 International Cross-Domain Conference, CD-MAKE 2023, Benevento, Italy, August 29 – September 1, 2023, proceedings SP - 31-44 PB - Springer Nature Switzerland CY - Cham, Switzerland SN - 978-3-031-40836-6 DO - 10.1007/978-3-031-40837-3_3 UR - https://fis.uni-bamberg.de/handle/uniba/93116 LA - eng AB - Research in the field of explainable artificial intelligence has produced a vast amount of visual explanation methods for deep learning-based image classification in various domains of application. However, there is still a lack of domain-specific evaluation methods to assess an explanation’s quality and a classifier’s performance with respect to domain-specific requirements. In particular, evaluation methods could benefit from integrating human expertise into quality criteria and metrics. Such domain-specific evaluation methods can help to assess the robustness of deep learning models more precisely. In this paper, we present an approach for domain-specific evaluation of visual explanation methods in order to enhance the transparency of deep learning models and estimate their robustness accordingly. As an example use case, we apply our framework to facial expression recognition. We can show that the domain-specific evaluation is especially beneficial for challenging use cases such as facial expression recognition and provides application-grounded quality criteria that are not covered by standard evaluation methods. Our comparison of the domain-specific evaluation method with standard approaches thus shows that the quality of the expert knowledge is of great importance for assessing a model’s performance precisely. KW - Application-Grounded Facial Expression Recognition ER - TY - JOUR TI - Semantic Interactive Learning for Text Classification : A Constructive Approach for Contextual Interactions AU - Kiefer, Sebastian AU - Hoffmann, Mareike AU - Schmid, Ute PY - 2023 SP - 994-1010 PB - Otto-Friedrich-Universität CY - Bamberg UR - https://fis.uni-bamberg.de/handle/uniba/92430 LA - eng AB - Interactive Machine Learning (IML) can enable intelligent systems to interactively learn from their end-users, and is quickly becoming more and more relevant to many application domains. Although it places the human in the loop, interactions are mostly performed via mutual explanations that miss contextual information. Furthermore, current model-agnostic IML strategies such as CAIPI are limited to ’destructive’ feedback, meaning that they solely allow an expert to prevent a learner from using irrelevant features. In this work, we propose a novel interaction framework called Semantic Interactive Learning for the domain of document classification, located at the intersection between Natural Language Processing (NLP) and Machine Learning (ML). We frame the problem of incorporating constructive and contextual feedback into the learner as a task involving finding an architecture that enables more semantic alignment between humans and machines while at the same time helping to maintain the statistical characteristics of the input domain when generating user-defined counterexamples based on meaningful corrections. Therefore, we introduce a technique called SemanticPush that is effective for translating conceptual corrections of humans to non-extrapolating training examples such that the learner’s reasoning is pushed towards the desired behavior. Through several experiments we show how our method compares to CAIPI, a state of the art IML strategy, in terms of Predictive Performance and Local Explanation Quality in downstream multi-class classification tasks. Especially in the early stages of interactions, our proposed method clearly outperforms CAIPI while allowing for contextual interpretation and intervention. Overall, SemanticPush stands out with regard to data efficiency, as it requires fewer queries from the pool dataset to achieve high accuracy. KW - human-centric machine learning KW - interactive machine learning KW - CAIPI KW - explainable artificial intelligence KW - local surrogate explanation models KW - contextual and semantic explanations KW - locally faithful explanations KW - topic modeling ER - TY - JOUR TI - Explanatory machine learning for justified trust in human-AI collaboration : Experiments on file deletion recommendations AU - Göbel, Kyra AU - Niessen, Cornelia AU - Seufert, Sebastian AU - Schmid, Ute PY - 2023 SP - 1-19 PB - Otto-Friedrich-Universität CY - Bamberg UR - https://fis.uni-bamberg.de/handle/uniba/92517 LA - eng AB - In the digital age, saving and accumulating large amounts of digital data is a common phenomenon. However, saving does not only consume energy, but may also cause information overload and prevent people from staying focused and working effectively. We present and systematically examine an explanatory AI system (Dare2Del), which supports individuals to delete irrelevant digital objects. To give recommendations for the optimization of related human-computer interactions, we vary different design features (explanations, familiarity, verifiability) within and across three experiments (N1 = 61, N2 = 33, N3= 73). Moreover, building on the concept of distributed cognition, we check possible cross-connections between external (digital) and internal (human) memory. Specifically, we examine whether deleting external files also contributes to human forgetting of the related mental representations. Multilevel modeling results show the importance of presenting explanations for the acceptance of deleting suggestions in all three experiments, but also point to the need of their verifiability to generate trust in the system. However, we did not find clear evidence that deleting computer files contributes to human forgetting of the related memories. Based on our findings, we provide basic recommendations for the design of AI systems that can help to reduce the burden on people and the digital environment, and suggest directions for future research. KW - distributed cognition KW - transactive memory KW - trust KW - forgetting KW - explainable AI KW - human-AI partnership ER - TY - JOUR TI - Explainable AI AU - Schmid, Ute AU - Wrede, Britta PY - 2023 SP - 207-210 PB - Otto-Friedrich-Universität CY - Bamberg UR - https://fis.uni-bamberg.de/handle/uniba/91689 LA - eng AB - - KW - AI ER - TY - JOUR TI - What is Missing in XAI So Far? : An Interdisciplinary Perspective AU - Schmid, Ute AU - Wrede, Britta PY - 2023 SP - 303-315 PB - Otto-Friedrich-Universität CY - Bamberg UR - https://fis.uni-bamberg.de/handle/uniba/91643 LA - eng AB - With the perspective on applications of AI-technology, especially data intensive deep learning approaches, the need for methods to control and understand such models has been recognized and gave rise to a new research domain labeled explainable artificial intelligence (XAI). In this overview paper we give an interim appraisal of what has been achieved so far and where there are still gaps in the research. We take an interdisciplinary perspective to identify challenges on XAI research and point to open questions with respect to the quality of the explanations regarding faithfulness and consistency of explanations. On the other hand we see a need regarding the interaction between XAI and user to allow for adaptability to specific information needs and explanatory dialog for informed decision making as well as the possibility to correct models and explanations by interaction. This endeavor requires an integrated interdisciplinary perspective and rigorous approaches to empirical evaluation based on psychological, linguistic and even sociological theories. KW - Explainable AI KW - Human-centred AI KW - Hybrid AI ER - TY - JOUR TI - ManuKnowVis : How to Support Different User Groups in Contextualizing and Leveraging Knowledge Repositories AU - Eirich, Joscha AU - Jackle, Dominik AU - Sedlmair, Michael AU - Wehner, Christoph AU - Schmid, Ute AU - Bernard, Jürgen AU - Schreck, Tobias PY - 2023 JO - IEEE transactions on visualization and computer graphics : TVCG VL - 29 IS - 8 SP - 3441-3457 PB - IEEE CY - New York SN - 1077-2626 DO - 10.1109/tvcg.2023.3279857 UR - https://fis.uni-bamberg.de/handle/uniba/90043 LA - eng ER - TY - CPAPER TI - Erwerb rekursiver Programmiertechniken aus Beispielfunktionen und Erklärungen AU - Schmid, Ute PY - 2023 SP - 247 PB - Otto-Friedrich-Universität CY - Bamberg DO - 10.20378/irb-58012 UR - https://fis.uni-bamberg.de/handle/uniba/58012 LA - deu AB - - KW - Studie ER - TY - CPAPER TI - Der Einfluß von Beispielähnlichkeit auf induktive Lernprozesse beim rekursiven Programmieren AU - Schmid, Ute AU - Kaup, Barbara PY - 2023 SP - 268 PB - Otto-Friedrich-Universität CY - Bamberg DO - 10.20378/irb-58009 UR - https://fis.uni-bamberg.de/handle/uniba/58009 LA - deu AB - - KW - Softwareentwicklung ER - TY - CPAPER TI - Deskription und Analyse komplexer Verhaltenssequenzen : Benutzerstrategien beim Arbeiten mit CAD-Systemen AU - Schmid, Ute PY - 2023 SP - 44 PB - Otto-Friedrich-Universität CY - Bamberg DO - 10.20378/irb-58016 UR - https://fis.uni-bamberg.de/handle/uniba/58016 LA - deu AB - - KW - Studie ER - TY - CPAPER TI - HiMLEdge : Energy-Aware Optimization for Hierarchical Machine Learning AU - Wissing, Julio AU - Scheele, Stephan AU - Mohammed, Aliya AU - Kolossa, Dorothea AU - Schmid, Ute PY - 2022 T2 - Advanced Research in Technologies, Information, Innovation and Sustainability : Second International Conference, ARTIIS 2022 Santiago de Compostela, Spain, September 12–15, 2022 ; Revised Selected Papers SP - 15-29 PB - Springer CY - Cham, Switzerland SN - 978-3-031-20315-2 DO - 10.1007/978-3-031-20316-9_2 UR - https://fis.uni-bamberg.de/handle/uniba/112624 LA - eng ER - TY - CPAPER TI - Data literacy in primary school teachers’ education and training AU - Gärtig-Daugs, Anja AU - Werner, Alexander AU - Troles, Jonas AU - Schneider, Adrian AU - Szczepaniak, Renata AU - Schmid, Ute PY - 2022 PB - ResearchGate DO - 10.13140/rg.2.2.34400.96000 UR - https://fis.uni-bamberg.de/handle/uniba/112080 LA - eng AB - The growing relevance of data-driven technologies in children’s everyday lives highlights the need to introduce fundamental data literacy concepts in primary education. To achieve this, primary school teachers must possess adequate data skills and know how to teach them effectively. A Massive Open Online Course (MOOC) was therefore developed to provide (prospective) primary school teachers with essential data literacy competencies, covering basic concepts, data evaluation and security, and introductory machine learning, complemented by ready-to-use teaching materials. Preliminary results from an ongoing evaluation show that participants are highly motivated, consider data literacy important for both their personal and professional lives, and generally rate their prior knowledge as moderate. Despite this, most feel capable of conveying data literacy after completing the course. These findings suggest that a MOOC is a suitable way to integrate data literacy into teacher education and to support its implementation in primary school classrooms. KW - data literacy KW - teacher education KW - massive online open course KW - teacher professionalisation ER - TY - JOUR TI - IRVINE : A Design Study on Analyzing Correlation Patterns of Electrical Engines AU - Eirich, Joscha AU - Bonart, Jakob AU - Jäckle, Dominik AU - Sedlmair, Michael AU - Schmid, Ute AU - Fischbach, Kai AU - Schreck, Tobias AU - Bernard, Jürgen PY - 2022 JO - IEEE transactions on visualization and computer graphics : TVCG VL - 28 IS - 1 SP - 11-21 PB - IEEE CY - New York, NY SN - 1077-2626 DO - 10.1109/tvcg.2021.3114797 UR - https://fis.uni-bamberg.de/handle/uniba/93294 LA - eng ER - TY - JOUR TI - Explaining and Evaluating Deep Tissue Classification by Visualizing Activations of Most Relevant Intermediate Layers AU - Mohammed, Aliya AU - Geppert, Carol AU - Hartmann, Arnd AU - Kuritcyn, Petr AU - Bruns, Volker AU - Schmid, Ute AU - Wittenberg, Thomas AU - Benz, Michaela AU - Finzel, Bettina PY - 2022 JO - Current directions in biomedical engineering VL - 8 IS - 2 SP - 229-232 PB - De Gruyter CY - Berlin SN - 2364-5504 DO - 10.1515/cdbme-2022-1059 UR - https://fis.uni-bamberg.de/handle/uniba/93000 LA - eng AB - Deep Learning-based tissue classification may support pathologists in analyzing digitized whole slide images. However, in such critical tasks, only approaches that can be validated by medical experts in advance to deployment, are suitable. We present an approach that contributes to making automated tissue classification more transparent. We step beyond broadly used visualizations for last layers of a convolutional neural network by identifying most relevant intermediate layers applying Grad-CAM. A visual evaluation by a pathologist shows that these layers assign relevance, where important morphological structures are present in case of correct class decisions. We introduce a tool that can be easily used by medical experts for such validation purposes for any convolutional neural network and any layer. Visual explanations for intermediate layers provide insights into a neural network’s decision for histopathological tissue classification. In future research also the context of the input data must be considered. KW - Digital Pathology KW - Deep Learning KW - XAI KW - Evaluation KW - Grad-CAM KW - Intelligent user interface ER - TY - JOUR TI - Explanatory machine learning for justified trust in human-AI collaboration : Experiments on file deletion recommendations AU - Göbel, Kyra AU - Niessen, Cornelia AU - Seufert, Sebastian AU - Schmid, Ute PY - 2022 JO - Frontiers in Artificial Intelligence VL - 5 IS - 919534 SP - 1-19 PB - Frontiers Media CY - Lausanne SN - 2624-8212 DO - 10.3389/frai.2022.919534 UR - https://fis.uni-bamberg.de/handle/uniba/92515 LA - eng AB - In the digital age, saving and accumulating large amounts of digital data is a common phenomenon. However, saving does not only consume energy, but may also cause information overload and prevent people from staying focused and working effectively. We present and systematically examine an explanatory AI system (Dare2Del), which supports individuals to delete irrelevant digital objects. To give recommendations for the optimization of related human-computer interactions, we vary different design features (explanations, familiarity, verifiability) within and across three experiments (N1 = 61, N2 = 33, N3= 73). Moreover, building on the concept of distributed cognition, we check possible cross-connections between external (digital) and internal (human) memory. Specifically, we examine whether deleting external files also contributes to human forgetting of the related mental representations. Multilevel modeling results show the importance of presenting explanations for the acceptance of deleting suggestions in all three experiments, but also point to the need of their verifiability to generate trust in the system. However, we did not find clear evidence that deleting computer files contributes to human forgetting of the related memories. Based on our findings, we provide basic recommendations for the design of AI systems that can help to reduce the burden on people and the digital environment, and suggest directions for future research. KW - distributed cognition KW - transactive memory KW - trust KW - forgetting KW - explainable AI KW - human-AI partnership ER - TY - CPAPER TI - Worked Examples as Application of Analogical Reasoning in Intelligent Tutoring and their Effects on SQL Competencies AU - Thaler, Anna Magdalena AU - Mitrovic, Antonija AU - Schmid, Ute PY - 2022 T2 - KogWis 2022 : understanding minds : 15th Biannual Conference of the German Society for Cognitive Science SP - 157-158 PB - Universität CY - Freiburg DO - 10.6094/UNIFR/229611 UR - https://fis.uni-bamberg.de/handle/uniba/92239 LA - eng AB - - KW - Intelligent Tutoring KW - SQL Competencies ER - TY - JOUR TI - Explainable AI AU - Schmid, Ute AU - Wrede, Britta PY - 2022 JO - Künstliche Intelligenz : KI ; Forschung, Entwicklung, Erfahrungen ; Organ des Fachbereichs 1 Künstliche Intelligenz der Gesellschaft für Informatik e.V., GI VL - 36 IS - 3-4 SP - 207-210 PB - Springer CY - Berlin SN - 0933-1875 DO - 10.1007/s13218-022-00788-0 UR - https://fis.uni-bamberg.de/handle/uniba/91644 LA - eng AB - - KW - AI ER - TY - JOUR TI - What is Missing in XAI So Far? : An Interdisciplinary Perspective AU - Schmid, Ute AU - Wrede, Britta PY - 2022 JO - Künstliche Intelligenz : KI ; Forschung, Entwicklung, Erfahrungen ; Organ des Fachbereichs 1 Künstliche Intelligenz der Gesellschaft für Informatik e.V., GI VL - 36 IS - 3-4 SP - 303-315 PB - Springer CY - Berlin SN - 0933-1875 DO - 10.1007/s13218-022-00786-2 UR - https://fis.uni-bamberg.de/handle/uniba/91641 LA - eng AB - With the perspective on applications of AI-technology, especially data intensive deep learning approaches, the need for methods to control and understand such models has been recognized and gave rise to a new research domain labeled explainable artificial intelligence (XAI). In this overview paper we give an interim appraisal of what has been achieved so far and where there are still gaps in the research. We take an interdisciplinary perspective to identify challenges on XAI research and point to open questions with respect to the quality of the explanations regarding faithfulness and consistency of explanations. On the other hand we see a need regarding the interaction between XAI and user to allow for adaptability to specific information needs and explanatory dialog for informed decision making as well as the possibility to correct models and explanations by interaction. This endeavor requires an integrated interdisciplinary perspective and rigorous approaches to empirical evaluation based on psychological, linguistic and even sociological theories. KW - Explainable AI KW - Human-centred AI KW - Hybrid AI ER - TY - JOUR TI - Semantic Interactive Learning for Text Classification : A Constructive Approach for Contextual Interactions AU - Kiefer, Sebastian AU - Hoffmann, Mareike AU - Schmid, Ute PY - 2022 JO - Machine learning and knowledge extraction VL - 4 IS - 4 SP - 994-1010 PB - MDPI CY - Basel SN - 2504-4990 DO - 10.3390/make4040050 UR - https://fis.uni-bamberg.de/handle/uniba/90352 LA - eng AB - Interactive Machine Learning (IML) can enable intelligent systems to interactively learn from their end-users, and is quickly becoming more and more relevant to many application domains. Although it places the human in the loop, interactions are mostly performed via mutual explanations that miss contextual information. Furthermore, current model-agnostic IML strategies such as CAIPI are limited to ’destructive’ feedback, meaning that they solely allow an expert to prevent a learner from using irrelevant features. In this work, we propose a novel interaction framework called Semantic Interactive Learning for the domain of document classification, located at the intersection between Natural Language Processing (NLP) and Machine Learning (ML). We frame the problem of incorporating constructive and contextual feedback into the learner as a task involving finding an architecture that enables more semantic alignment between humans and machines while at the same time helping to maintain the statistical characteristics of the input domain when generating user-defined counterexamples based on meaningful corrections. Therefore, we introduce a technique called SemanticPush that is effective for translating conceptual corrections of humans to non-extrapolating training examples such that the learner’s reasoning is pushed towards the desired behavior. Through several experiments we show how our method compares to CAIPI, a state of the art IML strategy, in terms of Predictive Performance and Local Explanation Quality in downstream multi-class classification tasks. Especially in the early stages of interactions, our proposed method clearly outperforms CAIPI while allowing for contextual interpretation and intervention. Overall, SemanticPush stands out with regard to data efficiency, as it requires fewer queries from the pool dataset to achieve high accuracy. KW - human-centric machine learning KW - interactive machine learning KW - CAIPI KW - explainable artificial intelligence KW - local surrogate explanation models KW - contextual and semantic explanations KW - locally faithful explanations KW - topic modeling ER - TY - JOUR TI - Constructing Explainability : Interdisciplinary Framework to Actively Shape Explanations in XAI AU - Schmid, Ute PY - 2022 JO - Künstliche Intelligenz : KI ; Forschung, Entwicklung, Erfahrungen ; Organ des Fachbereichs 1 Künstliche Intelligenz der Gesellschaft für Informatik e.V., GI VL - 36 IS - 3-4 SP - 327-331 PB - Springer CY - Berlin SN - 0933-1875 DO - 10.1007/s13218-022-00767-5 UR - https://fis.uni-bamberg.de/handle/uniba/89958 LA - eng ER - TY - GEN TI - Uni.vers Forschung : das Magazin der Otto-Friedrich-Universität Bamberg AU - Andresen, Maike AU - Bela, Anika AU - Carbon, Claus-Christian AU - Fischbach, Kai AU - Gebel, Michael AU - Gerholz, Karl-Heinz AU - Hebel, Vera AU - Heineck, Guido AU - Held, Marco AU - Hoffmann, Rasmus AU - Illies, Christian AU - Kroh, Jacqueline AU - Kunz, Miriam AU - Lautenbacher, Stefan AU - Maier, Christian AU - Rosseburg, Svenja AU - Saalfeld, Thomas AU - Schlagbauer, Lisa Marie AU - Schmid, Ute AU - Schütz, Astrid AU - Struck, Olaf AU - Vogt, Sabine AU - Volmer, Judith AU - Wied, Kristina AU - Zehelein, Eva-Sabine ED - Fischbach, Kai PY - 2022 IS - Mai 2022: Wissen über Gesundheit - Interdisziplinäre Forschung an der Universität Bamberg = Insights into Health - Interdisciplinary Research at the University of Bamberg PB - Otto-Friedrich-Universität CY - Bamberg SN - 1618-9019 UR - https://fis.uni-bamberg.de/handle/uniba/55051 LA - deu AB - Fühlen Sie sich gesund? Wie auch immer Ihre Antwort ausfällt: Wissen über Gesundheit ist wichtig, um sie zu erhalten. Dass die Nachfrage nach Informationen über Krankheiten groß ist, hat zuletzt die Corona-Pandemie offengelegt. Besonders gefragt waren die Fachbereiche Virologie und Medizin. Aber hätten Sie gedacht, dass auch die Disziplinen Soziologie, Wirtschaftsinformatik oder Geschichte wertvolle Impulse für ein gesundes Leben geben können? Die Stärke der Gesundheitsforschung an der Universität Bamberg liegt darin, dass sie Menschen ganzheitlich betrachtet. KW - Gesundheit KW - interdisziplinär KW - Wohlbefinden KW - Psychologie KW - Architektur KW - Burnout KW - Covid-19 KW - Digitalisierung KW - Demenz KW - App KW - Technostress KW - Ungleichheit KW - Pflege KW - Amerika ER - TY - CPAPER TI - CorrLoss : Integrating Co-Occurrence Domain Knowledge for Affect Recognition AU - Rieger, Ines AU - Pahl, Jaspar AU - Finzel, Bettina AU - Schmid, Ute PY - 2022 T2 - 2022 26th International Conference on Pattern Recognition (ICPR): Proceedings SP - 798-804 PB - IEEE SN - 978-1-6654-9062-7 DO - 10.1109/ICPR56361.2022.9956319 UR - https://fis.uni-bamberg.de/handle/uniba/58025 LA - eng ER - TY - CPAPER TI - Explainable Online Lane Change Predictions on a Digital Twin with a Layer Normalized LSTM and Layer-wise Relevance Propagation AU - Wehner, Christoph AU - Powlesland, Francis AU - Altakrouri, Bashar AU - Schmid, Ute PY - 2022 T2 - Advances and Trends in Artificial Intelligence. Theory and Practices in Artificial Intelligence : 35th International Conference on Industrial, Engineering and Other Applications of Applied Intelligent Systems, IEA/AIE 2022, Kitakyushu, Japan, July 19–22, 2022, Proceedings VL - 13343 SP - 621-632 T3 - LNCS DO - 10.1007/978-3-031-08530-7_52 UR - https://fis.uni-bamberg.de/handle/uniba/57284 LA - eng ER - TY - CPAPER TI - Extending Challenge Sets to Uncover Gender Bias in Machine Translation : Impact of Stereotypical Verbs and Adjectives AU - Troles, Jonas-Dario AU - Schmid, Ute PY - 2022 SP - 1-11 PB - Otto-Friedrich-Universität CY - Bamberg UR - https://fis.uni-bamberg.de/handle/uniba/56939 LA - eng AB - Human gender bias is reflected in language and text production. Because state-of-the-art machine translation (MT) systems are trained on large corpora of text, mostly generated by humans, gender bias can also be found in MT. For instance when occupations are translated from a language like English, which mostly uses gender neutral words, to a language like German, which mostly uses a feminine and a masculine version for an occupation, a decision must be made by the MT System. Recent research showed that MT systems are biased towards stereotypical translation of occupations. In 2019 the first, and so far only, challenge set, explicitly designed to measure the extent of gender bias in MT systems has been published. In this set measurement of gender bias is solely based on the translation of occupations. With our paper we present an extension of this challenge set, called WiBeMT, which adds gender-biased adjectives and sentences with gender-biased verbs. The resulting challenge set consists of over 70, 000 sentences and has been translated with three commercial MT systems: DeepL Translator, Microsoft Translator, and Google Translate. Results show a gender bias for all three MT systems. This gender bias is to a great extent significantly influenced by adjectives and to a lesser extent by verbs. KW - Gender Bias KW - Machine Translation KW - Challenge Set ER - TY - CHAP TI - Individuelle Förderung von Programmierfertigkeiten im Studium am Beispiel von Intelligenten Tutor Systemen für SQL AU - Thaler, Anna Magdalena AU - Paukner, Franziska Karin AU - Troles, Jonas-Dario AU - Schmid, Ute PY - 2022 SP - 61-77 PB - Otto-Friedrich-Universität CY - Bamberg UR - https://fis.uni-bamberg.de/handle/uniba/56834 LA - deu AB - Trotz vermehrter Technologisierung im (Hoch-)Schulkontext finden konkrete auf Künstlicher Intelligenz (KI) basierte Ansätze in den Lehr- und Lernumgebungen relativ wenig Anwendung. In diesem theoriebasierten Konzeptpapier erklären wir Einsatzmöglichkeiten von KI-basierten Methoden in der Hochschullehre anhand von sog. Intelligenten Tutor Systemen (ITS) im Anwendungskontext der Datenbanksprache SQL und allgemeiner Programmierfertigkeiten. Wir zeigen individuelle, technische und organisationale Rahmenbedingungen für eine erfolgreiche Umsetzung von ITS innerhalb der Hochschullehre auf. Es wird als Literaturüberblick dargestellt, wie mit ITS prozedurales und deklaratives Wissen ermittelt und die anzueignenden Fertigkeiten durch individuelles Feedback ausgebaut werden können. Insbesondere gehen wir dabei auf Overlay-Modelle und Algorithmic Debugging ein. Als interaktiver Feedbacktyp werden strukturanaloge Beispiele als Anwendung analogen Schlussfolgerns diskutiert. Als Reflexion des Forschungsprozesses beschäftigen wir uns mit relevanten theoretischen Überlegungen für die akademische Lehrpraxis, insbesondere der Schaffung einer offeneren Fehlerkultur und produktiven Scheiterns sowie kritischer Überlegungen zu Evaluationsmethoden bestehender ITS. KW - Intelligente Tutor Systeme KW - Strukturanaloge Beispiele KW - AI in Education ER - TY - CHAP TI - Individuelle Förderung von Programmierfertigkeiten im Studium am Beispiel von Intelligenten Tutor Systemen für SQL AU - Thaler, Anna Magdalena AU - Paukner, Franziska Karin AU - Troles, Jonas-Dario AU - Schmid, Ute PY - 2022 T2 - Scholarship of Teaching and Learning : Eine forschungsgeleitete Fundierung und Weiterentwicklung hochschul(fach)didaktischen Handelns SP - 61-77 CY - Köln DO - 10.57684/COS-986 UR - https://fis.uni-bamberg.de/handle/uniba/56860 LA - deu AB - Trotz vermehrter Technologisierung im (Hoch-)Schulkontext finden konkrete auf Künstlicher Intelligenz (KI) basierte Ansätze in den Lehr- und Lernumgebungen relativ wenig Anwendung. In diesem theoriebasierten Konzeptpapier erklären wir Einsatzmöglichkeiten von KI-basierten Methoden in der Hochschullehre anhand von sog. Intelligenten Tutor Systemen (ITS) im Anwendungskontext der Datenbanksprache SQL und allgemeiner Programmierfertigkeiten. Wir zeigen individuelle, technische und organisationale Rahmenbedingungen für eine erfolgreiche Umsetzung von ITS innerhalb der Hochschullehre auf. Es wird als Literaturüberblick dargestellt, wie mit ITS prozedurales und deklaratives Wissen ermittelt und die anzueignenden Fertigkeiten durch individuelles Feedback ausgebaut werden können. Insbesondere gehen wir dabei auf Overlay-Modelle und Algorithmic Debugging ein. Als interaktiver Feedbacktyp werden strukturanaloge Beispiele als Anwendung analogen Schlussfolgerns diskutiert. Als Reflexion des Forschungsprozesses beschäftigen wir uns mit relevanten theoretischen Überlegungen für die akademische Lehrpraxis, insbesondere der Schaffung einer offeneren Fehlerkultur und produktiven Scheiterns sowie kritischer Überlegungen zu Evaluationsmethoden bestehender ITS. KW - Intelligente Tutor Systeme KW - Strukturanaloge Beispiele KW - AI in Education ER - TY - CPAPER TI - Der Einfluß von Beispielähnlichkeit auf induktive Lernprozesse beim rekursiven Programmieren AU - Schmid, Ute AU - Kaup, Barbara PY - 2022 SP - 625 PB - Otto-Friedrich-Universität CY - Bamberg DO - 10.20378/irb-56130 UR - https://fis.uni-bamberg.de/handle/uniba/56130 LA - deu AB - . KW - - ER - TY - JOUR TI - Deskription und Analyse komplexer Verhaltenssequenzen : Benutzerstrategien beim Arbeiten mit CAD-Systemen AU - Schmid, Ute AU - Meseke, Bodo PY - 2022 PB - Otto-Friedrich-Universität CY - Bamberg DO - 10.20378/irb-56045 UR - https://fis.uni-bamberg.de/handle/uniba/56045 LA - deu AB - Es wird ein Verfahren vorgestellt, das es ermöglicht, Eingabesequenzen von Computeranwendern bei der Lösung einer komplexen Aufgabe zu vergleichen. Die individuellen Sequenzen werden in Markov-Ketten erster Ordnung umgewandelt. Die Ahnlichkeit dieser quadratischen Matrizen kann dann über die Abweichungen der Zellenwerte ermittelt werden. Es resultiert eine symmetrische Matrix der Sequenzdistanzen, die zu weiteren quantitativen Analysen (z.B. multidimensionale Skalierung) verwendet werden kann. Das Verfahren wird auf den Vergleich von Eingabeprotokollen bei der Arbeit mit einem CAD-System angewendet, um Hinweise auf unterschiedliche Benutzertypen zu erhalten. Die Sequenzunterschiede konnten auf zwei für die Arbeitseffektivität bedeutsame Benutzermerkmale - "adäquate Befehlsrepräsentation" und "Arbeitsstil" - zurückgeführt werden. KW - - ER - TY - JOUR TI - Zur Invarianz von Problemlösestilen über verschiedene Bereiche AU - Andresen, Norbert AU - Schmid, Ute PY - 2022 PB - Otto-Friedrich-Universität CY - Bamberg DO - 10.20378/irb-56043 UR - https://fis.uni-bamberg.de/handle/uniba/56043 LA - deu AB - Um zu prüfen, ob individuelle Problemlösestile über verschiedene Problembereiche hinweg invariante Merkmale aufweisen, wurden Probanden mit zwei sehr verschiedenen komplexen Aufgaben konfrontiert. Personen, deren unterschiedliches Arbeitsverhalten an einem CAD-System analysiert wurde, konnten zwei Jahre später dazu gewonnen werden, ein einfaches dynamisches System zu regeln. Für die CAD-Untersuchung wurden aus den Eingaben zur Erledigung einer Zeichenaufgabe quantitative Benutzerkennwerte ermittelt. Bei dem einfachen dynamischen System handelt es sich um die schon mehrfach publizierte Kühlhaus-Aufgabe. Diese wurde in zwei Durchgängen bearbeitet. Es wurden Kennwerte für den Problemlösungsverlauf und die Lösungsgüte entwickelt. Zusätzlich wurden ein Maß der Allgemeinen Intelligenz und das über das System erworbene Wissen erhoben. Es stellten sich bedeutsame Zusammenhänge zwischen den Kennwerten für die zweite Systemregelung und den übrigen Variablen heraus: Verlaufsmerkmale der zweiten Regelung lassen sich aus dem Verlauf der ersten Regelung vorhersagen. Steuerungsgüte und erworbenes Systemwissen werden durch Merkmale der individuellen CAD-Problemlösungen vorhergesagt. Die Allgemeine Intelligenz ist dagegen, wie in vielen Untersuchungen bestätigt, kein tauglicher Prädiktor für komplexes Problemlöseverhalten. KW - - ER - TY - CPAPER TI - Transfer beim Umgang mit einem einfachen dynamischen System AU - Andresen, Norbert AU - Schmid, Ute PY - 2022 SP - 2-3 PB - Otto-Friedrich-Universität CY - Bamberg DO - 10.20378/irb-56132 UR - https://fis.uni-bamberg.de/handle/uniba/56132 LA - deu AB - . KW - - ER - TY - CPAPER TI - Female, white, 27? : Bias Evaluation on Data and Algorithms for Affect Recognition in Faces AU - Pahl, Jaspar AU - Rieger, Ines AU - Möller, Anna AU - Wittenberg, Thomas AU - Schmid, Ute PY - 2022 SP - 973-987 PB - Otto-Friedrich-Universität CY - Bamberg UR - https://fis.uni-bamberg.de/handle/uniba/55613 LA - eng AB - Nowadays, Artificial Intelligence (AI) algorithms show a strong performance for many use cases, making them desirable for real-world scenarios where the algorithms provide high-impact decisions. However, one major drawback of AI algorithms is their susceptibility to bias and resulting unfairness. This has a huge influence for their application, as they have a higher failure rate for certain subgroups. In this paper, we focus on the field of affective computing and particularly on the detection of bias for facial expressions. Depending on the deployment scenario, bias in facial expression models can have a disadvantageous impact and it is therefore essential to evaluate the bias and limitations of the model. In order to analyze the metadata distribution in affective computing datasets, we annotate several benchmark training datasets, containing both Action Units and categorical emotions, with age, gender, ethnicity, glasses, and beards. We show that there is a significantly skewed distribution, particularly for ethnicity and age. Based on this metadata annotation, we evaluate two trained state-of-the-art affective computing algorithms. Our evaluation shows that the strongest bias is in age, with the best performance for persons under 34 and a sharp decrease for older persons. Furthermore, we see an ethnicity bias with varying direction depending on the algorithm, a slight gender bias and worse performance for facial parts occluded by glasses. KW - affective computing KW - action units KW - categorical emotions KW - metadata post-annotation KW - bias KW - fairness KW - data evaluation, KW - algorithm evaluation ER - TY - JOUR TI - Mutual Explanations for Cooperative Decision Making in Medicine AU - Schmid, Ute AU - Finzel, Bettina PY - 2022 SP - 227-233 PB - Otto-Friedrich-Universität CY - Bamberg UR - https://fis.uni-bamberg.de/handle/uniba/55221 LA - eng AB - Exploiting mutual explanations for interactive learning is presented as part of an interdisciplinary research project on transparent machine learning for medical decision support. Focus of the project is to combine deep learning black box approaches with interpretable machine learning for classification of different types of medical images to combine the predictive accuracy of deep learning and the transparency and comprehensibility of interpretable models. Specifically, we present an extension of the Inductive Logic Programming system Aleph to allow for interactive learning. Medical experts can ask for verbal explanations. They can correct classification decisions and in addition can also correct the explanations. Thereby, expert knowledge can be taken into account in form of constraints for model adaption. KW - Human-AI partnership KW - Inductive Logic Programming KW - Explanations as constraints ER - TY - CHAP TI - Künstliche Intelligenz und Psychologie - Von Kognitiver Modellierung bis Erklärbarkeit AU - Schmid, Ute AU - Weitz, Katharina PY - 2022 T2 - Psychologie : eine Einführung in ihre Grundlagen und Anwendungsfelder SP - 219-231 PB - Kohlhammer CY - Stuttgart ET - 6., überarbeitete Auflage SN - 978-3-17-041364-1 UR - https://fis.uni-bamberg.de/handle/uniba/55621 LA - deu ER - TY - CPAPER TI - Deriving Temporal Prototypes from Saliency Map Clusters for the Analysis of Deep-Learning-based Facial Action Unit Classification AU - Finzel, Bettina AU - Kollmann, Rene AU - Rieger, Ines AU - Pahl, Jaspar AU - Schmid, Ute PY - 2022 SP - 86-97 PB - Otto-Friedrich-Universität CY - Bamberg UR - https://fis.uni-bamberg.de/handle/uniba/55380 LA - eng AB - Reliably determining the emotional state of a person is a difficult task for both humans as well as machines. Automatic detection and evaluation of facial expressions is particularly important if people are unable to express their emotional state themselves, for example due to cognitive impairments. Identifying the presence of Action Units in a human’s face is a psychologically validated approach of quantifying which emotion is expressed. To automate the detection process of Action Units Neural Networks have been trained. However, the black-box nature of Deep Neural Networks provides no insight on the relevant features identified during the decision process. Approaches of Explainable Artificial Intelligence have to be applied to provide an explanation why the network came to a certain conclusion. In this work "Layer-Wise Relevance Propagation" (LRP) in combination with the meta analysis approach "Spectral Relevance Analysis" (SpRAy) is used to derive temporal prototypes from predictions in video sequences. Temporal prototypes provide an aggregated view on the prediction of the network by grouping together similar frames by considering relevance. Additionally, a specific visualization method for temporal prototypes is presented that highlights the most relevant areas for a prediction of an Action Unit. A quantitative evaluation of our approach shows that temporal prototypes aggregate temporal information well. The proposed method can be used to generate concise visual explanations for a sequence of interpretable saliency maps. Based on the above, this work shall provide the foundation for a new temporal analysis method as well as an explanation approach that is supposed to help researchers and experts to gain a deeper understanding of how the underlying network decides which Action Units are active in a particular emotional state. KW - Temporal Prototypes KW - Facial Action Unit Detection KW - Layer-wise Relevance Propagation KW - Spectral Clustering KW - Affective Computing KW - Correlation Analysis ER - TY - CPAPER TI - Female, white, 27? : Bias Evaluation on Data and Algorithms for Affect Recognition in Faces AU - Pahl, Jaspar AU - Rieger, Ines AU - Möller, Anna AU - Wittenberg, Thomas AU - Schmid, Ute PY - 2022 T2 - FAccT '22: 2022 ACM Conference on Fairness, Accountability, and Transparency : 2022 Proceeding SP - 973-987 PB - Association for Computing Machinery SN - 978-1-4503-9352-2 DO - 10.1145/3531146.3533159 UR - https://fis.uni-bamberg.de/handle/uniba/55036 LA - eng AB - Nowadays, Artificial Intelligence (AI) algorithms show a strong performance for many use cases, making them desirable for real-world scenarios where the algorithms provide high-impact decisions. However, one major drawback of AI algorithms is their susceptibility to bias and resulting unfairness. This has a huge influence for their application, as they have a higher failure rate for certain subgroups. In this paper, we focus on the field of affective computing and particularly on the detection of bias for facial expressions. Depending on the deployment scenario, bias in facial expression models can have a disadvantageous impact and it is therefore essential to evaluate the bias and limitations of the model. In order to analyze the metadata distribution in affective computing datasets, we annotate several benchmark training datasets, containing both Action Units and categorical emotions, with age, gender, ethnicity, glasses, and beards. We show that there is a significantly skewed distribution, particularly for ethnicity and age. Based on this metadata annotation, we evaluate two trained state-of-the-art affective computing algorithms. Our evaluation shows that the strongest bias is in age, with the best performance for persons under 34 and a sharp decrease for older persons. Furthermore, we see an ethnicity bias with varying direction depending on the algorithm, a slight gender bias and worse performance for facial parts occluded by glasses. KW - affective computing KW - action units KW - categorical emotions KW - metadata post-annotation KW - bias KW - fairness KW - data evaluation, KW - algorithm evaluation ER - TY - JOUR TI - Generating contrastive explanations for inductive logic programming based on a near miss approach AU - Rabold, Johannes AU - Siebers, Michael AU - Schmid, Ute PY - 2022 VL - 111 SP - 1799-1820 UR - https://fis.uni-bamberg.de/handle/uniba/54696 LA - eng AB - In recent research, human-understandable explanations of machine learning models have received a lot of attention. Often explanations are given in form of model simplifications or visualizations. However, as shown in cognitive science as well as in early AI research, concept understanding can also be improved by the alignment of a given instance for a concept with a similar counterexample. Contrasting a given instance with a structurally similar example which does not belong to the concept highlights what characteristics are necessary for concept membership. Such near misses have been proposed by Winston (Learning structural descriptions from examples, 1970) as efficient guidance for learning in relational domains. We introduce an explanation generation algorithm for relational concepts learned with Inductive Logic Programming (GeNME). The algorithm identifies near miss examples from a given set of instances and ranks these examples by their degree of closeness to a specific positive instance. A modified rule which covers the near miss but not the original instance is given as an explanation. We illustrate GeNME with the well-known family domain consisting of kinship relations, the visual relational Winston arches domain, and a real-world domain dealing with file management. We also present a psychological experiment comparing human preferences of rule-based, example-based, and near miss explanations in the family and the arches domains. KW - Explainable AI KW - Relational concepts KW - Contrastive explanations KW - Inductive logic programming KW - Near miss examples ER - TY - JOUR TI - Automatic Coding of Facial Expressions of Pain: Are We There Yet? AU - Lautenbacher, Stefan AU - Hassan, Teena AU - Seuß, Dominik AU - Loy, Frederik AU - Garbas, Jens-Uwe AU - Schmid, Ute AU - Kunz, Miriam PY - 2022 PB - Otto-Friedrich-Universität CY - Bamberg UR - https://fis.uni-bamberg.de/handle/uniba/54266 LA - eng AB - Introduction. The experience of pain is regularly accompanied by facial expressions. The gold standard for analyzing these facial expressions is the Facial Action Coding System (FACS), which provides so-called action units (AUs) as parametrical indicators of facial muscular activity. Particular combinations of AUs have appeared to be pain-indicative. The manual coding of AUs is, however, too time- and labor-intensive in clinical practice. New developments in automatic facial expression analysis have promised to enable automatic detection of AUs, which might be used for pain detection. Objective. Our aim is to compare manual with automatic AU coding of facial expressions of pain. Methods. FaceReader7 was used for automatic AU detection. We compared the performance of FaceReader7 using videos of 40 participants (20 younger with a mean age of 25.7 years and 20 older with a mean age of 52.1 years) undergoing experimentally induced heat pain to manually coded AUs as gold standard labeling. Percentages of correctly and falsely classified AUs were calculated, and we computed as indicators of congruency, “sensitivity/recall,” “precision,” and “overall agreement (F1).” Results. The automatic coding of AUs only showed poor to moderate outcomes regarding sensitivity/recall, precision, and F1. The congruency was better for younger compared to older faces and was better for pain-indicative AUs compared to other AUs. Conclusion. At the moment, automatic analyses of genuine facial expressions of pain may qualify at best as semiautomatic systems, which require further validation by human observers before they can be used to validly assess facial expressions of pain. KW - pain KW - facial expression KW - coding ER - TY - JOUR TI - Automatic Coding of Facial Expressions of Pain: Are We There Yet? AU - Lautenbacher, Stefan AU - Hassan, Teena AU - Seuß, Dominik AU - Loy, Frederik AU - Garbas, Jens-Uwe AU - Schmid, Ute AU - Kunz, Miriam PY - 2022 JO - Pain research & management VL - 2022 PB - Hindawi CY - London [u.a.] SN - 1918-1523 DO - 10.1155/2022/6635496 UR - https://fis.uni-bamberg.de/handle/uniba/54265 LA - eng AB - Introduction. The experience of pain is regularly accompanied by facial expressions. The gold standard for analyzing these facial expressions is the Facial Action Coding System (FACS), which provides so-called action units (AUs) as parametrical indicators of facial muscular activity. Particular combinations of AUs have appeared to be pain-indicative. The manual coding of AUs is, however, too time- and labor-intensive in clinical practice. New developments in automatic facial expression analysis have promised to enable automatic detection of AUs, which might be used for pain detection. Objective. Our aim is to compare manual with automatic AU coding of facial expressions of pain. Methods. FaceReader7 was used for automatic AU detection. We compared the performance of FaceReader7 using videos of 40 participants (20 younger with a mean age of 25.7 years and 20 older with a mean age of 52.1 years) undergoing experimentally induced heat pain to manually coded AUs as gold standard labeling. Percentages of correctly and falsely classified AUs were calculated, and we computed as indicators of congruency, “sensitivity/recall,” “precision,” and “overall agreement (F1).” Results. The automatic coding of AUs only showed poor to moderate outcomes regarding sensitivity/recall, precision, and F1. The congruency was better for younger compared to older faces and was better for pain-indicative AUs compared to other AUs. Conclusion. At the moment, automatic analyses of genuine facial expressions of pain may qualify at best as semiautomatic systems, which require further validation by human observers before they can be used to validly assess facial expressions of pain. KW - pain KW - facial expression KW - coding ER - TY - CPAPER TI - Explaining Machine Learned Relational Concepts in Visual Domains : Effects of Perceived Accuracy on Joint Performance and Trust AU - Thaler, Anna Magdalena AU - Schmid, Ute PY - 2022 SP - 7 PB - Otto-Friedrich-Universität CY - Bamberg UR - https://fis.uni-bamberg.de/handle/uniba/52972 LA - eng AB - Most machine learning based decision support systems are black box models that are not interpretable for humans. However, the demand for explainable models to create comprehensible and trustworthy systems is growing, particularly in complex domains involving risky decisions. In many domains, decision making is based on visual information. We argue that nevertheless, explanations need to be verbal to communicate the relevance of specific feature values and critical relations for a classification decision. To address that claim, we introduce a fictitious visual domain from archeology where aerial views of ancient grave sites must be classified. Trustworthiness among other factors relies on the perceived or assumed correctness of a system's decisions. Models learned by induction of data, in general, cannot have perfect predictive accuracy and one can assume that unexplained erroneous system decisions might reduce trust. In a 2×2 factorial online experiment with 190 participants, we investigated the effect of verbal explanations and information about system errors. Our results show that explanations increase comprehension of the factors on which classification of grave sites is based and that explanations increase the joint performance of human and system for new decision tasks. Furthermore, explanations result in more confidence in decision making and higher trust in the system. KW - Explainability KW - Verbal Explanations KW - Prediction Errors KW - Trust KW - Relational Learning ER - TY - JOUR TI - Warum KI auch ein Thema für die Kita ist AU - Schmid, Ute Maria PY - 2021 JO - Das Kita-Handbuch CY - Berlin SN - 2751-4072 UR - https://fis.uni-bamberg.de/handle/uniba/112212 LA - deu ER - TY - CPAPER TI - A Case-Based Reasoning Approach for a Decision Support System in Manufacturing AU - Lang, Sascha AU - Plenk, Valentin AU - Schmid, Ute PY - 2021 T2 - Advances and Trends in Artificial Intelligence : From Theory to Practice : 34th International Conference on Industrial, Engineering and Other Applications of Applied Intelligent Systems, IEA/AIE 2021, Kuala Lumpur, Malaysia, July 26–29, 2021, Proceedings, Part II SP - 265-271 PB - Springer International Publishing T3 - Lecture Notes in Artificial Intelligence SN - 978-3-030-79462-0 DO - 10.1007/978-3-030-79463-7_22 UR - https://fis.uni-bamberg.de/handle/uniba/111298 LA - eng ER - TY - CPAPER TI - Anomaly Detection for Hydraulic Systems under Test AU - Neufeld, Deniz AU - Schmid, Ute PY - 2021 T2 - 2021 26th IEEE International Conference on Emerging Technologies and Factory Automation (ETFA ) SP - 1-8 PB - IEEE SN - 978-1-7281-2989-1 DO - 10.1109/etfa45728.2021.9613265 UR - https://fis.uni-bamberg.de/handle/uniba/111239 LA - eng ER - TY - CPAPER TI - Explanation as a Process : User-Centric Construction of Multi-level and Multi-modal Explanations AU - Finzel, Bettina AU - Tafler, David E. AU - Scheele, Stephan M. AU - Schmid, Ute PY - 2021 T2 - KI 2021: Advances in Artificial Intelligence : 44th German Conference on AI, Virtual Event, September 27 – October 1, 2021, Proceedings SP - 80–94 PB - Springer International Publishing CY - Cham T3 - Lecture Notes in Computer Science SN - 978-3-030-87626-5 DO - 10.1007/978-3-030-87626-5_7 UR - https://fis.uni-bamberg.de/handle/uniba/111166 LA - eng ER - TY - JOUR TI - Automatic Detection of Pain from Facial Expressions : A Survey AU - Hassan, Teena AU - Seuß, Dominik AU - Wollenberg, Johannes AU - Weitz, Katharina AU - Kunz, Miriam AU - Lautenbacher, Stefan AU - Garbas, Jens-Uwe AU - Schmid, Ute PY - 2021 JO - IEEE transactions on pattern analysis and machine intelligence : TPAMI VL - 43 IS - 6 SP - 1815-1831 PB - IEEE CY - New York, NY SN - 1939-3539 DO - 10.1109/tpami.2019.2958341 UR - https://fis.uni-bamberg.de/handle/uniba/111128 LA - eng ER - TY - CPAPER TI - Extending Challenge Sets to Uncover Gender Bias in Machine Translation : Impact of Stereotypical Verbs and Adjectives AU - Troles, Jonas-Dario AU - Schmid, Ute PY - 2021 T2 - Sixth Conference on Machine Translation : proceedings of the conference SP - 531–541 PB - Association for Computational Linguistics (ACL) CY - Stroudsburg, PA SN - 978-1-954085-94-7 UR - https://fis.uni-bamberg.de/handle/uniba/57197 LA - eng AB - Human gender bias is reflected in language and text production. Because state-of-the-art machine translation (MT) systems are trained on large corpora of text, mostly generated by humans, gender bias can also be found in MT. For instance when occupations are translated from a language like English, which mostly uses gender neutral words, to a language like German, which mostly uses a feminine and a masculine version for an occupation, a decision must be made by the MT System. Recent research showed that MT systems are biased towards stereotypical translation of occupations. In 2019 the first, and so far only, challenge set, explicitly designed to measure the extent of gender bias in MT systems has been published. In this set measurement of gender bias is solely based on the translation of occupations. With our paper we present an extension of this challenge set, called WiBeMT, which adds gender-biased adjectives and sentences with gender-biased verbs. The resulting challenge set consists of over 70, 000 sentences and has been translated with three commercial MT systems: DeepL Translator, Microsoft Translator, and Google Translate. Results show a gender bias for all three MT systems. This gender bias is to a great extent significantly influenced by adjectives and to a lesser extent by verbs. KW - Gender Bias KW - Machine Translation KW - Challenge Set ER - TY - CPAPER TI - Deriving Temporal Prototypes from Saliency Map Clusters for the Analysis of Deep-Learning-based Facial Action Unit Classification AU - Finzel, Bettina AU - Kollmann, Rene AU - Rieger, Ines AU - Pahl, Jaspar AU - Schmid, Ute PY - 2021 T2 - Proceedings of the LWDA 2021 Workshops: FGWM, KDML, FGWI-BIA, and FGIR SP - 86-97 PB - RWTH Aachen CY - Aachen, Germany UR - https://fis.uni-bamberg.de/handle/uniba/55037 LA - eng AB - Reliably determining the emotional state of a person is a difficult task for both humans as well as machines. Automatic detection and evaluation of facial expressions is particularly important if people are unable to express their emotional state themselves, for example due to cognitive impairments. Identifying the presence of Action Units in a human’s face is a psychologically validated approach of quantifying which emotion is expressed. To automate the detection process of Action Units Neural Networks have been trained. However, the black-box nature of Deep Neural Networks provides no insight on the relevant features identified during the decision process. Approaches of Explainable Artificial Intelligence have to be applied to provide an explanation why the network came to a certain conclusion. In this work "Layer-Wise Relevance Propagation" (LRP) in combination with the meta analysis approach "Spectral Relevance Analysis" (SpRAy) is used to derive temporal prototypes from predictions in video sequences. Temporal prototypes provide an aggregated view on the prediction of the network by grouping together similar frames by considering relevance. Additionally, a specific visualization method for temporal prototypes is presented that highlights the most relevant areas for a prediction of an Action Unit. A quantitative evaluation of our approach shows that temporal prototypes aggregate temporal information well. The proposed method can be used to generate concise visual explanations for a sequence of interpretable saliency maps. Based on the above, this work shall provide the foundation for a new temporal analysis method as well as an explanation approach that is supposed to help researchers and experts to gain a deeper understanding of how the underlying network decides which Action Units are active in a particular emotional state. KW - Temporal Prototypes KW - Facial Action Unit Detection KW - Layer-wise Relevance Propagation KW - Spectral Clustering KW - Affective Computing KW - Correlation Analysis ER - TY - GEN TI - Uni.vers Forschung : das Magazin der Otto-Friedrich-Universität Bamberg AU - Achter, Patricia AU - Braches-Chyrek, Rita AU - Düchs, Martin AU - Färber, Tanja AU - Finzel, Bettina AU - Ganesch, Franziska AU - Graichen, Joanna AU - Horn, Matthias AU - Oehler, Andreas AU - Posegga, Oliver AU - Proaño Acosta, Christian AU - Scheltjens, Werner AU - Schmid, Ute AU - Schneider, Pauline AU - Staake, Thorsten AU - Steins-Löber, Sabine AU - Stingl, Carlo AU - Stöckl, Andreas AU - Struck, Olaf AU - Velde, Caroline van der AU - Wolstein, Jörg ED - Fischbach, Kai PY - 2021 IS - April 2021, Mensch und Maschine - Bamberger Beiträge zur Digitalisierung = Man and Machine - Bamberg Scholars on Digitalisation PB - Otto-Friedrich-Universität CY - Bamberg SN - 1618-9019 UR - https://fis.uni-bamberg.de/handle/uniba/50041 LA - deu AB - Wenn Menschen die Technik weiterentwickeln, entstehen ständig neue Möglichkeiten und Herausforderungen. Die Gesellschaft ist gefragt mitzudiskutieren, wie eine immer weiter digitalisierte Welt künftig aussehen könnte. Und die Forschung hilft dabei, dass sich jede und jeder Einzelne eine fundierte Meinung bilden kann. In dieser Ausgabe schreiben die Autorinnen und Autoren über den Einsatz der Technik im Alltag, die Zusammenarbeit von Menschen und Maschinen, das Pro und Contra der Digitalisierung. KW - Digitalisierung KW - Technik KW - KI KW - Gesellschaft KW - App KW - Internet KW - Arbeitsmarkt KW - Geschichte KW - Psychologie KW - Architektur KW - Kinder KW - Medien KW - Finanzen KW - Gesundheit ER - TY - CPAPER TI - Explaining Machine Learned Relational Concepts in Visual Domains : Effects of Perceived Accuracy on Joint Performance and Trust AU - Thaler, Anna Magdalena AU - Schmid, Ute PY - 2021 VL - 43 SP - 1705-1711 SN - 1069-7977 UR - https://fis.uni-bamberg.de/handle/uniba/53481 LA - eng AB - Most machine learning based decision support systems are black box models that are not interpretable for humans. However, the demand for explainable models to create comprehensible and trustworthy systems is growing, particularly in complex domains involving risky decisions. In many domains, decision making is based on visual information. We argue that nevertheless, explanations need to be verbal to communicate the relevance of specific feature values and critical relations for a classification decision. To address that claim, we introduce a fictitious visual domain from archeology where aerial views of ancient grave sites must be classified. Trustworthiness among other factors relies on the perceived or assumed correctness of a system's decisions. Models learned by induction of data, in general, cannot have perfect predictive accuracy and one can assume that unexplained erroneous system decisions might reduce trust. In a 2×2 factorial online experiment with 190 participants, we investigated the effect of verbal explanations and information about system errors. Our results show that explanations increase comprehension of the factors on which classification of grave sites is based and that explanations increase the joint performance of human and system for new decision tasks. Furthermore, explanations result in more confidence in decision making and higher trust in the system. KW - Explainability KW - Verbal Explanations KW - Prediction Errors KW - Trust KW - Relational Learning ER - TY - BOOK TI - Handbuch der Künstlichen Intelligenz ED - Görz, Günther ED - Schmid, Ute ED - Braun, Tanya PY - 2021 PB - De Gruyter CY - Berlin ; Boston ET - 6 SN - 978-3-11-065984-9 DO - 10.1515/9783110659948 UR - https://fis.uni-bamberg.de/handle/uniba/52974 LA - deu ER - TY - JOUR TI - Informatische Bildung und Medienbildung in der Grundschule im Kontext der Bildung für nachhaltige Entwicklung (BNE) : Umsetzungsbeispiele für das Thema Gesundheit und Wohlbefinden. AU - Gärtig-Daugs, Anja AU - Müller, Linda AU - Schween, Hendrik AU - Werner, Alexander AU - Schmid, Ute PY - 2021 JO - Grundschule : 1 bis 4 : Konzepte, Praxistipps, Best Practice, Lehrkraftkompetenzen PB - mgo fachverlage CY - Kulmbach UR - https://fis.uni-bamberg.de/handle/uniba/52586 LA - deu ER - TY - CPAPER TI - Grundkonzepte des Maschinellen Lernens für die Grundschule : Algorithmen, Bias, Generalisierungsfehler AU - Schmid, Ute AU - Gärtig-Daugs, Anja AU - Müller, Linda AU - Werner, Alexander PY - 2021 T2 - INFORMATIK 2021 : Computer Science & Sustainability : 27. September – 01. Oktober 2021, Berlin : Proceedings SP - 1611-1623 PB - Köllen CY - Bonn DO - 10.18420/informatik2021-135 UR - https://fis.uni-bamberg.de/handle/uniba/52585 LA - deu ER - TY - JOUR TI - Lehrkräfte auf die digitale Transformation an Schulen vorbereiten : DigiLLabs als Innovationszentren in der Lehrerbildung an der Universität Bamberg AU - Gärtig-Daugs, Anja AU - Dücker, Lisa AU - Gerholz, Karl-Heinz AU - Groß, Jorge AU - Lindner, Konstantin AU - Paul, Jürgen AU - Schmid, Ute AU - Steinweg, Anna Susanne AU - Struck, Olaf AU - Szczepaniak, Renata PY - 2021 JO - Schulverwaltung : Bayern IS - 10 PB - Link CY - Kronach ; München ; Bonn SN - 0170-091X UR - https://fis.uni-bamberg.de/handle/uniba/52584 LA - deu ER - TY - JOUR TI - Generating contrastive explanations for inductive logic programming based on a near miss approach AU - Rabold, Johannes AU - Siebers, Michael AU - Schmid, Ute PY - 2021 JO - Machine Learning VL - 111 SP - 1799-1820 PB - Springer Science + Business Media B.V CY - Dordrecht [u.a.] SN - 0885-6125 DO - 10.1007/s10994-021-06048-w UR - https://fis.uni-bamberg.de/handle/uniba/51715 LA - eng AB - In recent research, human-understandable explanations of machine learning models have received a lot of attention. Often explanations are given in form of model simplifications or visualizations. However, as shown in cognitive science as well as in early AI research, concept understanding can also be improved by the alignment of a given instance for a concept with a similar counterexample. Contrasting a given instance with a structurally similar example which does not belong to the concept highlights what characteristics are necessary for concept membership. Such near misses have been proposed by Winston (Learning structural descriptions from examples, 1970) as efficient guidance for learning in relational domains. We introduce an explanation generation algorithm for relational concepts learned with Inductive Logic Programming (GeNME). The algorithm identifies near miss examples from a given set of instances and ranks these examples by their degree of closeness to a specific positive instance. A modified rule which covers the near miss but not the original instance is given as an explanation. We illustrate GeNME with the well-known family domain consisting of kinship relations, the visual relational Winston arches domain, and a real-world domain dealing with file management. We also present a psychological experiment comparing human preferences of rule-based, example-based, and near miss explanations in the family and the arches domains. KW - Explainable AI KW - Relational concepts KW - Contrastive explanations KW - Inductive logic programming KW - Near miss examples ER - TY - JOUR TI - Beneficial and harmful explanatory machine learning AU - Ai, Lun AU - Muggleton, Stephen H. AU - Hocquette, Céline AU - Gromowski, Mark AU - Schmid, Ute PY - 2021 JO - Machine learning VL - 110 IS - 4 SP - 695–721 PB - Springer CY - Dordrecht SN - 0885-6125 DO - 10.1007/s10994-020-05941-0 UR - https://fis.uni-bamberg.de/handle/uniba/51179 LA - eng AB - Given the recent successes of Deep Learning in AI there has been increased interest in the role and need for explanations in machine learned theories. A distinct notion in this context is that of Michie’s definition of ultra-strong machine learning (USML). USML is demonstrated by a measurable increase in human performance of a task following provision to the human of a symbolic machine learned theory for task performance. A recent paper demonstrates the beneficial effect of a machine learned logic theory for a classification task, yet no existing work to our knowledge has examined the potential harmfulness of machine’s involvement for human comprehension during learning. This paper investigates the explanatory effects of a machine learned theory in the context of simple two person games and proposes a framework for identifying the harmfulness of machine explanations based on the Cognitive Science literature. The approach involves a cognitive window consisting of two quantifiable bounds and it is supported by empirical evidence collected from human trials. Our quantitative and qualitative results indicate that human learning aided by a symbolic machine learned theory which satisfies a cognitive window has achieved significantly higher performance than human self learning. Results also demonstrate that human learning aided by a symbolic machine learned theory that fails to satisfy this window leads to significantly worse performance than unaided human learning. KW - Critical Thinking KW - Instructional Theory KW - Learning Theory KW - Machine Learning KW - Symbolic AI KW - Artificial Intelligence ER - TY - CHAP TI - Künstliche Intelligenz in Unternehmen - Zielgruppen-spezifische KI-Kompetenzen identifizieren und vermitteln AU - Schmid, Ute AU - Bruckert, Sebastian PY - 2021 T2 - Handbuch Digitale Kompetenzentwicklung : wie sich Unternehmen auf die digitale Zukunft vorbereiten SP - 187–201 PB - Hanser CY - München SN - 978-3-446-46907-5 DO - 10.3139/9783446469075 UR - https://fis.uni-bamberg.de/handle/uniba/50957 LA - deu ER - TY - CHAP TI - Explainability is not Enough : Requirements for Human-AI-Partnership in Complex Socio-Technical Systems AU - Waefler, Toni AU - Schmid, Ute PY - 2021 SP - 185-194 PB - Otto-Friedrich-Universität CY - Bamberg DO - 10.20378/irb-49775 UR - https://fis.uni-bamberg.de/handle/uniba/49775 LA - eng AB - Explainability has been recognized as an important requirement of artificial intelligence (AI) systems. Transparent decision policies and explanations regarding why an AI system comes about a certain decision is a pre-requisite if AI is supposed to support human decision-making or if human-AI collaborative decision-making is envisioned. Human-AI interaction and joint decision-making is required in many real-world domains, where risky decisions have to be made (e.g. medical diagnosis) or complex situations have to be assessed (e.g. states of machines or production processes). However, in this paper we theorize that explainability is necessary but not sufficient. Coming from the point of view of work psychology we argue that for the human part of the human-AI system much more is required than intelligibility. In joint human-AI decision-making a certain role is assigned to the human, which normally encompasses tasks such as (i) verifying AI based decision suggestions, (ii) improving AI systems, (iii) learning from AI systems, and (iv) taking responsibility for the final decision as well as for compliance with legislation and ethical standards. Empowering the human to take this demanding role requires not only human expertise but e.g. also human motivation, which is triggered by a suitable task design. Furthermore, at work humans normally do not take decisions as lonely wolves but in formal and informal cooperation with other humans. Hence, to design effective explainability and to empower for true human-AI collaborative decision-making, embedding human-AI dyads into a socio-technical context is necessary. Coming from theory, this paper presents system design criteria on different levels substantiated by work psychology. The criteria are described and confronted with a use case scenario of AI-supported medical decision making in the context of digital pathology. On this basis, the need for further research is outlined. KW - Companion Technology, Explainable AI, Interactive Learning, Human Factors, Socio-Technical Systems, Motivation ER - TY - JOUR TI - Stop Thinking : An Experience Sampling Study on Suppressing Distractive Thoughts at Work AU - Niessen, Cornelia AU - Göbel, Kyra AU - Lang, Jonas W. B. AU - Schmid, Ute PY - 2021 SP - 1-12 PB - Otto-Friedrich-Universität CY - Bamberg UR - https://fis.uni-bamberg.de/handle/uniba/49766 LA - eng AB - In modern work environments, it can be difficult for workers to avoid becoming distracted from their current task. This study investigates person–situation interactions to predict thought control activities (kind of self-control), which aim to stop distracting thoughts that enter the mind. Specifically, it was examined (1) how challenging work demands (time pressure, task complexity) activate workers’ thought control to stop distractive thoughts (nlevel2 = 143) and relate to the effort to do so (nlevel2 = 91) in daily working life and (2) how these relationships differ according workers’ general cognitive ability to suppress unwanted thoughts. To understand these person–situation interactions, an experience sampling study was combined with a laboratory task assessing the ability to suppress unwanted thoughts (think/no-think task). Multilevel modeling revealed that workers’ engage more often and more intensively in thought control activities at a moderate level of time pressure but only when they had a higher general ability to suppress unwanted thoughts. For workers with a lower ability to suppress unwanted thoughts, increasing time pressure was negatively related to thought control activities, even at very low levels of time pressure. Thus, whether time pressure activates or hinders thought control depends on individuals’ ability to suppress distractive thoughts. KW - suppression-induced forgetting, thought control, self-control, time pressure, experience sampling ER - TY - JOUR TI - Special issue on “Learning in data science: theory, methods and applications” : preface by the guest editors AU - Baier, Daniel AU - Lausen, Berthold AU - Montanari, Angela AU - Schmid, Ute PY - 2020 JO - Advances in data analysis and classification : ADAC IS - Online first PB - Springer CY - Berlin ; Heidelberg SN - 1862-5355 DO - 10.1007/s11634-020-00431-6 UR - https://fis.uni-bamberg.de/handle/uniba/112641 LA - eng ER - TY - JOUR TI - KI ist nie perfekt AU - Schmid, Ute PY - 2020 JO - Didacta : das Magazin für lebenslanges Lernen IS - 3 SP - 42-44 PB - AVR, Agentur für Werbung und Produktion CY - München UR - https://fis.uni-bamberg.de/handle/uniba/112213 LA - deu ER - TY - JOUR TI - Die KI als Nachhilfelehrer AU - Schmid, Ute Maria PY - 2020 JO - Didacta : das Magazin für lebenslanges Lernen IS - 2 SP - 51 PB - AVR, Agentur für Werbung und Produktion CY - München UR - https://fis.uni-bamberg.de/handle/uniba/112214 LA - deu ER - TY - JOUR TI - Time to Forget : Intentional Forgetting in the Digital World of Work AU - Niessen, Cornelia AU - Göbel, Kyra AU - Siebers, Michael AU - Schmid, Ute PY - 2020 JO - Zeitschrift für Arbeits- und Organisationspsychologie : A & O VL - 64 IS - 1 SP - 30-45 PB - Hogrefe CY - Göttingen ; Stuttgart SN - 0932-4089 DO - 10.1026/0932-4089/a000308 UR - https://fis.uni-bamberg.de/handle/uniba/110277 LA - eng AB - Emerging technologies at work encourage the collection and storage of large amounts of data. However, these vast quantities of data are likely to impair efficient work decisions by employees over time, with negative consequences for the organization. As human attention increasingly represents the scarce resource at work, the present paper focuses on a mechanism of attentional control at work – namely, intentionally forgetting unwanted and outdated internal (e. g., knowledge) and external (e. g., digital objects) information. The purpose of this paper is threefold. Based on a short review of the research on intentional forgetting, a prototypical conceptualization of an interactive assistive system (Dare2Del, cognitive companion) is provided, which should support employees in temporally ignoring or permanently deleting outdated information. Then, we completed a critical incident study to examine why and when employees might want to forget information at work, and to identify in which working situations an assistive system should be particularly helpful. KW - information overload KW - intentional forgetting KW - self-control ER - TY - CHAP TI - Inductive Programming AU - Flener, Pierre AU - Schmid, Ute Maria PY - 2020 T2 - Encyclopedia of Machine Learning and Data Mining SP - 658–666 PB - Springer US CY - New York, NY SN - 9781489976857 DO - 10.1007/978-1-4899-7687-1_137 UR - https://fis.uni-bamberg.de/handle/uniba/93052 LA - eng ER - TY - JOUR TI - The Next Generation of Medical Decision Support : A Roadmap Toward Transparent Expert Companions AU - Bruckert, Sebastian AU - Finzel, Bettina AU - Schmid, Ute PY - 2020 JO - Frontiers in artificial intelligence VL - 3 PB - Frontiers Media CY - Lausanne SN - 2624-8212 DO - 10.3389/frai.2020.507973 UR - https://fis.uni-bamberg.de/handle/uniba/57747 LA - eng AB - Increasing quality and performance of artificial intelligence (AI) in general and machine learning (ML) in particular is followed by a wider use of these approaches in everyday life. As part of this development, ML classifiers have also gained more importance for diagnosing diseases within biomedical engineering and medical sciences. However, many of those ubiquitous high-performing ML algorithms reveal a black-box-nature, leading to opaque and incomprehensible systems that complicate human interpretations of single predictions or the whole prediction process. This puts up a serious challenge on human decision makers to develop trust, which is much needed in life-changing decision tasks. This paper is designed to answer the question how expert companion systems for decision support can be designed to be interpretable and therefore transparent and comprehensible for humans. On the other hand, an approach for interactive ML as well as human-in-the-loop-learning is demonstrated in order to integrate human expert knowledge into ML models so that humans and machines act as companions within a critical decision task. We especially address the problem of Semantic Alignment between ML classifiers and its human users as a prerequisite for semantically relevant and useful explanations as well as interactions. Our roadmap paper presents and discusses an interdisciplinary yet integrated Comprehensible Artificial Intelligence (cAI)-transition-framework with regard to the task of medical diagnosis. We explain and integrate relevant concepts and research areas to provide the reader with a hands-on-cookbook for achieving the transition from opaque black-box models to interactive, transparent, comprehensible and trustworthy systems. To make our approach tangible, we present suitable state of the art methods with regard to the medical domain and include a realization concept of our framework. The emphasis is on the concept of Mutual Explanations (ME) that we introduce as a dialog-based, incremental process in order to provide human ML users with trust, but also with stronger participation within the learning process. KW - explainable artificial intelligence KW - interactive ML KW - interpretability KW - trust KW - medical diagnosis KW - medical decision support KW - companion ER - TY - CPAPER TI - KI 2020: advances in artificial intelligence : 43rd German Conference on AI, Bamberg, Germany, September 21–25, 2020, proceedings ED - Schmid, Ute ED - Klügl, Franziska ED - Wolter, Diedrich PY - 2020 PB - Springer CY - Cham, Switzerland T3 - Lecture notes in computer science; Lecture notes in artificial intelligence SN - 9783030582845 DO - 10.1007/978-3-030-58285-2 UR - https://fis.uni-bamberg.de/handle/uniba/55355 LA - eng ER - TY - JOUR TI - Stop Thinking: An Experience Sampling Study on Suppressing Distractive Thoughts at Work AU - Niessen, Cornelia AU - Göbel, Kyra AU - Lang, Jonas W. B. AU - Schmid, Ute PY - 2020 JO - Frontiers in psychology VL - 11 IS - 1616 SP - 1-12 SN - 1664-1078 DO - 10.3389/fpsyg.2020.01616 UR - https://fis.uni-bamberg.de/handle/uniba/54112 LA - eng AB - In modern work environments, it can be difficult for workers to avoid becoming distracted from their current task. This study investigates person–situation interactions to predict thought control activities (kind of self-control), which aim to stop distracting thoughts that enter the mind. Specifically, it was examined (1) how challenging work demands (time pressure, task complexity) activate workers’ thought control to stop distractive thoughts (nlevel2 = 143) and relate to the effort to do so (nlevel2 = 91) in daily working life and (2) how these relationships differ according workers’ general cognitive ability to suppress unwanted thoughts. To understand these person–situation interactions, an experience sampling study was combined with a laboratory task assessing the ability to suppress unwanted thoughts (think/no-think task). Multilevel modeling revealed that workers’ engage more often and more intensively in thought control activities at a moderate level of time pressure but only when they had a higher general ability to suppress unwanted thoughts. For workers with a lower ability to suppress unwanted thoughts, increasing time pressure was negatively related to thought control activities, even at very low levels of time pressure. Thus, whether time pressure activates or hinders thought control depends on individuals’ ability to suppress distractive thoughts. KW - suppression-induced forgetting, thought control, self-control, time pressure, experience sampling ER - TY - JOUR TI - A process framework for inducing and explaining Datalog theories AU - Gromowski, Mark AU - Siebers, Michael AU - Schmid, Ute PY - 2020 JO - Advances in data analysis and classification : ADAC ; theory, methods, and applications in data science VL - 14 IS - 4 SP - 821–835 PB - Springer CY - Berlin SN - 1862-5347 DO - 10.1007/s11634-020-00422-7 UR - https://fis.uni-bamberg.de/handle/uniba/51178 LA - eng ER - TY - CHAP TI - Explainability is not Enough : Requirements for Human-AI-Partnership in Complex Socio-Technical Systems AU - Waefler, Toni AU - Schmid, Ute PY - 2020 T2 - Proceedings of the 2nd European Conference on the Impact of Artificial Intelligence and Robotics (ECIAIR 2020) SP - 185-194 PB - ACPIL CY - Lissabon SN - 9781912764747 DO - 10.34190/EAIR.20.007 UR - https://fis.uni-bamberg.de/handle/uniba/49781 LA - eng AB - Explainability has been recognized as an important requirement of artificial intelligence (AI) systems. Transparent decision policies and explanations regarding why an AI system comes about a certain decision is a pre-requisite if AI is supposed to support human decision-making or if human-AI collaborative decision-making is envisioned. Human-AI interaction and joint decision-making is required in many real-world domains, where risky decisions have to be made (e.g. medical diagnosis) or complex situations have to be assessed (e.g. states of machines or production processes). However, in this paper we theorize that explainability is necessary but not sufficient. Coming from the point of view of work psychology we argue that for the human part of the human-AI system much more is required than intelligibility. In joint human-AI decision-making a certain role is assigned to the human, which normally encompasses tasks such as (i) verifying AI based decision suggestions, (ii) improving AI systems, (iii) learning from AI systems, and (iv) taking responsibility for the final decision as well as for compliance with legislation and ethical standards. Empowering the human to take this demanding role requires not only human expertise but e.g. also human motivation, which is triggered by a suitable task design. Furthermore, at work humans normally do not take decisions as lonely wolves but in formal and informal cooperation with other humans. Hence, to design effective explainability and to empower for true human-AI collaborative decision-making, embedding human-AI dyads into a socio-technical context is necessary. Coming from theory, this paper presents system design criteria on different levels substantiated by work psychology. The criteria are described and confronted with a use case scenario of AI-supported medical decision making in the context of digital pathology. On this basis, the need for further research is outlined. KW - Companion Technology, Explainable AI, Interactive Learning, Human Factors, Socio-Technical Systems, Motivation ER - TY - CPAPER TI - Expressive Explanations of DNNs by Combining Concept Analysis with ILP AU - Rabold, Johannes AU - Schwalbe, Gesina AU - Schmid, Ute PY - 2020 T2 - KI 2020: Advances in Artificial Intelligence ; 43rd German Conference on AI, Bamberg, Germany, September 21–25, 2020, Proceedings SP - 148-162 PB - Springer CY - Cham SN - 978-3-030-58284-5 DO - 10.1007/978-3-030-58285-2_11 UR - https://fis.uni-bamberg.de/handle/uniba/49263 LA - eng ER - TY - CPAPER TI - Verifying Deep Learning-based Decisions for Facial Expression Recognition AU - Rieger, Ines AU - Kollmann, Rene AU - Finzel, Bettina AU - Seuß, Dominik AU - Schmid, Ute PY - 2020 T2 - ESANN 2020 proceedings SP - 139-144 SN - 978-2-87587-074-2 UR - https://fis.uni-bamberg.de/handle/uniba/49224 LA - eng ER - TY - JOUR TI - The Next Generation of Medical Decision Support : A Roadmap Toward Transparent Expert Companions AU - Bruckert, Sebastian AU - Finzel, Bettina AU - Schmid, Ute PY - 2020 IS - 507973 PB - Otto-Friedrich-Universität CY - Bamberg UR - https://fis.uni-bamberg.de/handle/uniba/49222 LA - eng AB - Increasing quality and performance of artificial intelligence (AI) in general and machine learning (ML) in particular is followed by a wider use of these approaches in everyday life. As part of this development, ML classifiers have also gained more importance for diagnosing diseases within biomedical engineering and medical sciences. However, many of those ubiquitous high-performing ML algorithms reveal a black-box-nature, leading to opaque and incomprehensible systems that complicate human interpretations of single predictions or the whole prediction process. This puts up a serious challenge on human decision makers to develop trust, which is much needed in life-changing decision tasks. This paper is designed to answer the question how expert companion systems for decision support can be designed to be interpretable and therefore transparent and comprehensible for humans. On the other hand, an approach for interactive ML as well as human-in-the-loop-learning is demonstrated in order to integrate human expert knowledge into ML models so that humans and machines act as companions within a critical decision task. We especially address the problem of Semantic Alignment between ML classifiers and its human users as a prerequisite for semantically relevant and useful explanations as well as interactions. Our roadmap paper presents and discusses an interdisciplinary yet integrated Comprehensible Artificial Intelligence (cAI)-transition-framework with regard to the task of medical diagnosis. We explain and integrate relevant concepts and research areas to provide the reader with a hands-on-cookbook for achieving the transition from opaque black-box models to interactive, transparent, comprehensible and trustworthy systems. To make our approach tangible, we present suitable state of the art methods with regard to the medical domain and include a realization concept of our framework. The emphasis is on the concept of Mutual Explanations (ME) that we introduce as a dialog-based, incremental process in order to provide human ML users with trust, but also with stronger participation within the learning process. KW - explainable artificial intelligence KW - interactive ML KW - interpretability KW - trust KW - medical diagnosis KW - medical decision support KW - companion ER - TY - CHAP TI - Hilf`mir die digitale Welt analog zu begreifen : Eine qualitative Studie zum Anregen von "Wie funktioniert das?"-Fragen durch die Experimentierkiste Informatik AU - Werner, Alexander AU - Gärtig-Daugs, Anja AU - Schmid, Ute PY - 2020 T2 - Digitale Bildung im Grundschulalter : Grundsatzfragen zum Primat des Pädagogischen SP - 357-373 PB - kopaed CY - München SN - 978-3-86736-543-7 UR - https://fis.uni-bamberg.de/handle/uniba/48684 LA - deu AB - Digitale Medien sind aus der heutigen Lebens- und Arbeitswelt nicht mehr wegzudenken. Entsprechend rückt die Förderung medienbezogener Kompetenzen auch in den Fokus der schulischen Bildung. Der vorliegende Beitrag stellt den Ansatz der Experimentierkiste Informatik zur Verzahnung medienpädagogischer Themen mit informatischer Grundbildung vor. Die Experimentierkiste richtet sich an Vor- und Grundschulkinder. Sie will Kinder zu einer forschenden Grundhaltung anregen und sie animieren, die Funktionsweise technischer Geräte nicht ungefragt als gegeben hinzunehmen, sondern ‘Wie-funktioniert-das?’-Fragen zu stellen. In einem quasi-experimentellen Design wurde untersucht, in welchem Grad das Bearbeiten der Experimentiermaterialien dazu anregt, digitale Medien zu hinterfragen. Durchgeführt wurde die Studie mit zwei ersten Klassen einer Grundschule. Beide Gruppen wurden nach einer Unterrichtseinheit, in der sie ein Tablet zum freien Malen verwenden durften, interviewt. Die Experimentalgruppe erhielt eine Intervention zum korrespondierenden Thema ‘Pixel’ vor dieser Unterrichtseinheit, die Kontrollgruppe danach. Untersucht wurden Forschungsfragen zur Formulierung freier Fragen, zur Beschreibung der Mediennutzung und informatischer Konzepte und zum Interesse zu diesem Thema. Erwartet wurde, dass in der Experimentalbedingung häufiger Fragen nach der Funktionsweise (z. B. ‘Wie-funktioniert das?’-Fragen), oder dem Lebensweltbezug gestellt werden und die Fragen eher eine erschaffende denn konsumierende Dimension der Nutzung widerspiegeln (z. B. Bilder malen vs. Videos schauen). Für die Kontrollbedingung hingegen wurden mehr Fragen aus den Kategorien, die eher auf eine oberflächliche Rezeption des Mediums schließen lassen (z. B. Kosten eines Geräts), erwartet. Die Ergebnisse zeigen, dass viele Kinder in der Lage sind, über ihre Mediennutzung und informatischen Themen zu sprechen und ein Teil auch zum Fragenstellen angeregt werden können. Große Unterschiede bezüglich der Aussagenkategorien ließen sich zwischen den Gruppen jedoch nicht feststellen. Tendenziell konnten Hinweise auf einen Einfluss auf das Interesse durch die Intervention beobachtet werden. Die Ergebnisse werden im Anschluss diskutiert. KW - Grundschule, Informatik, Experimentierkiste ER - TY - CPAPER TI - Gemeinsame mentale Modelle in der agilen Softwareentwicklung : Ein Ansatz zur Erstellung von Gestaltungsempfehlungen für “gute” erfahrungsspezifische User Stories. AU - Hallmann, Daniel AU - Schmid, Ute AU - Weth, Rüdiger von der PY - 2020 PB - Otto-Friedrich-Universität CY - Bamberg DO - 10.20378/irb-48184 UR - https://fis.uni-bamberg.de/handle/uniba/48184 LA - deu AB - User Stories sind ein probates Mittel zum Austausch von Anforderungen in der agilen Softwareentwicklung. Die Anwendung ist jedoch kritisch, da sich immer wieder Fehler in der Beschreibung einzelner Formularfelder wie den Akzeptanzkriterien einschleichen. Mit diesen fehlerhaften User Stories müssen Personen mit individuellen Erfahrungen ein gemeinsames mentales Modell konstruieren. Häufig ist der Aufbau jedoch nicht möglich und es kommt zu negativen Reaktionen wie Frustration bei fehlenden Erfahrungen, langen Diskussionen bei unterschiedlichen Vorstellungen und teuren Nacharbeiten bei missverstandenen Inhalten. Aufgrund dieser Effekte sollen mit einer Ex-post-Analyse, einer Feldstudie und einem Experiment die Zusammenhänge von fehlerhaften User Stories, individuellen Erfahrungen und gemeinsamen mentalen Modellen untersucht werden. Mit dieser Sicht auf die Verarbeitung von User Stories wird das Forschungsinteresse für kognitionspsychologische Prozesse in der agilen Softwareentwicklung unterstützt. Außerdem liefert die Arbeit für die Praxis Gestaltungsempfehlungen für „gute“ erfahrungsspezifische User Stories. Mit dieser Strategie sollen frühzeitig die Kosten in der agilen Softwareentwicklung reduziert werden. KW - Agile Softwareentwicklung KW - Qualität von User Stories KW - Kognitive Psychologie KW - Erfahrungen KW - Gemeinsame Mentale Modelle ER - TY - RPRT TI - Concept Enforcement and Modularization for the ISO 26262 Safety Case of Neural Networks AU - Schwalbe, Gesina AU - Schmid, Ute PY - 2020 PB - Otto-Friedrich-Universität CY - Bamberg DO - 10.20378/irb-47277 UR - https://fis.uni-bamberg.de/handle/uniba/47277 LA - eng AB - The ability to formulate formally verifiable requirements is crucial for the safety verification of software units in the automotive industries. However, it is very restricted for complex perception tasks involving deep neural networks (DNNs) due to their black-box character. For a solution we propose to identify or enforce human interpretable concepts as intermediate output of the DNN. Two effects are expected: Requirements can be formulated using these concepts. And the DNN is modularized, thus reduces complexity and therefore easing a safety case. A research project proposal for a PhD thesis is sketched in the following. KW - ISO 26262 KW - neural networks KW - formal verification KW - concept enforcement ER - TY - CHAP TI - Informatik in Kindergarten und Grundschule AU - Gärtig-Daugs, Anja AU - Steinhäuser, Anke AU - Weitz, Katharina AU - Neubauer, Carina AU - Schweibold, Andreas AU - Schmid, Ute PY - 2020 T2 - Kooperation von Kita und Grundschule SP - 136-170 PB - Carl Link Verlag CY - Köln SN - 978-3-556-07374-2 UR - https://fis.uni-bamberg.de/handle/uniba/47990 LA - deu ER - TY - JOUR TI - Von Algorithmen und Pixeln : Wie informatische Grundlagen analog vermittelt werden können AU - Werner, Alexander AU - Gärtig-Daugs, Anja AU - Schmid, Ute PY - 2020 JO - Uni.vers Forschung : das Magazin der Otto-Friedrich-Universität Bamberg IS - Mai : Lernen, ein Leben lang. Bamberger Beiträge zur Bildungsforschung SP - 16-19 CY - Bamberg SN - 2195-2558 UR - https://fis.uni-bamberg.de/handle/uniba/47981 LA - deu ER - TY - JOUR TI - Please delete that! Why should I? : Explaining learned irrelevance classifications of digital objects AU - Siebers, Michael AU - Schmid, Ute PY - 2020 PB - Otto-Friedrich-Universität CY - Bamberg DO - 10.20378/irb-46644 UR - https://fis.uni-bamberg.de/handle/uniba/46644 LA - eng KW - Irrelevant digital objects KW - Verbal explanations KW - Inductive Logic Programming ER - TY - JOUR TI - Mutual Explanations for Cooperative Decision Making in Medicine AU - Schmid, Ute AU - Finzel, Bettina PY - 2020 JO - Künstliche Intelligenz : KI ; Forschung, Entwicklung, Erfahrungen VL - 34 IS - 2 SP - 227-233 PB - Springer CY - Berlin ; Heidelberg SN - 1610-1987 DO - 10.1007/s13218-020-00633-2 UR - https://fis.uni-bamberg.de/handle/uniba/47120 LA - eng AB - Exploiting mutual explanations for interactive learning is presented as part of an interdisciplinary research project on transparent machine learning for medical decision support. Focus of the project is to combine deep learning black box approaches with interpretable machine learning for classification of different types of medical images to combine the predictive accuracy of deep learning and the transparency and comprehensibility of interpretable models. Specifically, we present an extension of the Inductive Logic Programming system Aleph to allow for interactive learning. Medical experts can ask for verbal explanations. They can correct classification decisions and in addition can also correct the explanations. Thereby, expert knowledge can be taken into account in form of constraints for model adaption. KW - Human-AI partnership KW - Inductive Logic Programming KW - Explanations as constraints ER - TY - CHAP TI - Was the Year 2000 a Leap Year? : Step-wise Narrowing Theories with Metagol AU - Siebers, Michael AU - Schmid, Ute PY - 2020 SP - 15 PB - Otto-Friedrich-Universität CY - Bamberg DO - 10.20378/irb-46649 UR - https://fis.uni-bamberg.de/handle/uniba/46649 LA - eng ER - TY - RPRT TI - Concept Enforcement and Modularization for the ISO 26262 Safety Case of Neural Networks AU - Schwalbe, Gesina AU - Schmid, Ute PY - 2019 PB - PhD Forum at the European Conference on Machine Learning and Principles of Knowledge Discovery (ECML) CY - Würzburg UR - https://fis.uni-bamberg.de/handle/uniba/54048 LA - eng AB - The ability to formulate formally verifiable requirements is crucial for the safety verification of software units in the automotive industries. However, it is very restricted for complex perception tasks involving deep neural networks (DNNs) due to their black-box character. For a solution we propose to identify or enforce human interpretable concepts as intermediate output of the DNN. Two effects are expected: Requirements can be formulated using these concepts. And the DNN is modularized, thus reduces complexity and therefore easing a safety case. A research project proposal for a PhD thesis is sketched in the following. KW - ISO 26262 KW - neural networks KW - formal verification KW - concept enforcement ER - TY - JOUR TI - Deep-learned faces of pain and emotions : Elucidating the differences of facial expressions with the help of explainable AI methods AU - Weitz, Katharina AU - Hassan, Teena AU - Schmid, Ute AU - Garbas, Jens-Uwe PY - 2019 JO - Technisches Messen : tm ; Sensoren, Geräte, Systeme VL - 86 IS - 7-8 SP - 404-412 PB - De Gruyter CY - Berlin SN - 2196-7113 DO - 10.1515/teme-2019-0024 UR - https://fis.uni-bamberg.de/handle/uniba/53497 LA - eng ER - TY - BOOK TI - Künstliche Intelligenz selber programmieren für Dummies Junior AU - Schmid, Ute AU - Weitz, Katharina AU - Siebers, Michael PY - 2019 PB - Wiley CY - Weinheim SN - 9783527715732 UR - https://fis.uni-bamberg.de/handle/uniba/48619 LA - deu ER - TY - CHAP TI - Effect of Superpixel Aggregation on Explanations in LIME - A Case Study with Biological Data AU - Schallner, Ludwig AU - Rabold, Johannes AU - Scholz, Oliver AU - Schmid, Ute PY - 2019 T2 - Machine Learning and Knowledge Discovery in Databases International Workshops of ECML PKDD 2019, Würzburg, Germany, September 16–20, 2019, Proceedings SP - 147-158 PB - Springer CY - Cham SN - 978-3-030-43822-7 DO - 10.1007/978-3-030-43823-4_13 UR - https://fis.uni-bamberg.de/handle/uniba/48484 LA - eng ER - TY - CHAP TI - Enriching Visual with Verbal Explanations for Relational Concepts – Combining LIME with Aleph AU - Rabold, Johannes AU - Deininger, Hannah AU - Siebers, Michael AU - Schmid, Ute PY - 2019 T2 - Machine Learning and Knowledge Discovery in Databases International Workshops of ECML PKDD 2019, Würzburg, Germany, September 16–20, 2019, Proceedings SP - 180-192 PB - Springer CY - Cham SN - 978-3-030-43822-7 DO - 10.1007/978-3-030-43823-4_16 UR - https://fis.uni-bamberg.de/handle/uniba/48483 LA - eng ER - TY - CPAPER TI - Wie funktioniert das? : Informatische Konzepte in der Vor- und Grundschule spielerisch begreifen und anwenden AU - Gärtig-Daugs, Anja AU - Werner, Alexander AU - Schmid, Ute PY - 2019 T2 - Informatik für alle : 18. GI-Fachtagung Informatik und Schule, 16.-18. September 2019 Dortmund SP - 377 CY - Bonn SN - 978-3-88579-682-4 UR - https://fis.uni-bamberg.de/handle/uniba/47982 LA - deu ER - TY - JOUR TI - Intentional Forgetting in Socio-Digital Work Systems. System Characteristics and User-related Psychological Consequences on Emotion, Cognition, and Behavior AU - Ellwart, Thomas AU - Ulfert, Anna-Sophie AU - Antoni, Conny Herbert AU - Becker, Jörg AU - Frings, Christian AU - Göbel, Kyra AU - Hertel, Guido AU - Kluge, Anette AU - Meeßen, Sarah M. AU - Niessen, Cornelia AU - Nohe, Christoph AU - Riehle, Dennis M. AU - Runge, Yannick AU - Schmid, Ute AU - Schüffler, Arnulf S. AU - Siebers, Michael AU - Sonnentag, Sabine AU - Tempel, Tobias AU - Thielsch, Meinald T. AU - Wehrt, Wilken PY - 2019 JO - AIS-Transactions on Enterprise Systems VL - 4 IS - 1 PB - GITO-Publ., Verl. für Industrielle Informationstechnik und Organisation CY - Berlin DO - 10.30844/aistes.v4i1.16 UR - https://fis.uni-bamberg.de/handle/uniba/46642 LA - eng ER - TY - JOUR TI - Please delete that! Why should I? Explaining learned irrelevance classifications of digital objects AU - Siebers, Michael AU - Schmid, Ute PY - 2019 JO - Künstliche Intelligenz : KI ; Forschung, Entwicklung, Erfahrungen ; Organ des Fachbereichs 1 Künstliche Intelligenz der Gesellschaft für Informatik e.V., GI VL - 33 IS - 1 SP - 35-44 PB - Springer CY - Berlin SN - 1610-1987 DO - 10.1007/s13218-018-0565-5 UR - https://fis.uni-bamberg.de/handle/uniba/46921 LA - eng KW - Irrelevant digital objects KW - Verbal explanations KW - Inductive Logic Programming ER - TY - CHAP TI - Intentional Forgetting in Artificial Intelligence Systems : Perspectives and Challenges AU - Timm, Ingo J. AU - Staab, Steffen AU - Siebers, Michael AU - Schon, Claudia AU - Schmid, Ute AU - Sauerwald, Kai AU - Reuter, Lukas AU - Ragni, Marco AU - Niederée, Claudia AU - Maus, Heiko AU - Kern-Isberner, Gabriele AU - Jilek, Christian AU - Friemann, Paulina AU - Eiter, Thomas AU - Dengel, Andreas AU - Dames, Hannah AU - Bock, Tanja AU - Berndt, Jan Ole AU - Beierle, Christoph PY - 2019 PB - Otto-Friedrich-Universität CY - Bamberg DO - 10.20378/irb-46646 UR - https://fis.uni-bamberg.de/handle/uniba/46646 LA - eng ER - TY - JOUR TI - Ultra-Strong Machine Learning: comprehensibility of programs learned with ILP AU - Muggleton, Stephen H. AU - Schmid, Ute AU - Zeller, Christina AU - Tamaddoni-Nezhad, Alireza AU - Besold, Tarek PY - 2018 SP - 1119-1140 PB - Otto-Friedrich-Universität CY - Bamberg UR - https://fis.uni-bamberg.de/handle/uniba/53799 LA - eng AB - During the 1980s Michie defined Machine Learning in terms of two orthogonal axes of performance: predictive accuracy and comprehensibility of generated hypotheses. Since predictive accuracy was readily measurable and comprehensibility not so, later definitions in the 1990s, such as Mitchell’s, tended to use a one-dimensional approach to Machine Learning based solely on predictive accuracy, ultimately favouring statistical over symbolic Machine Learning approaches. In this paper we provide a definition of comprehensibility of hypotheses which can be estimated using human participant trials. We present two sets of experiments testing human comprehensibility of logic programs. In the first experiment we test human comprehensibility with and without predicate invention. Results indicate comprehensibility is affected not only by the complexity of the presented program but also by the existence of anonymous predicate symbols. In the second experiment we directly test whether any state-of-the-art ILP systems are ultra-strong learners in Michie’s sense, and select the Metagol system for use in humans trials. Results show participants were not able to learn the relational concept on their own from a set of examples but they were able to apply the relational definition provided by the ILP system correctly. This implies the existence of a class of relational concepts which are hard to acquire for humans, though easy to understand given an abstract explanation. We believe improved understanding of this class could have potential relevance to contexts involving human learning, teaching and verbal interaction. KW - Inductive logic programming KW - Comprehensibility KW - ultra-strong machine learning ER - TY - JOUR TI - Ultra-Strong Machine Learning: comprehensibility of programs learned with ILP AU - Muggleton, Stephen H. AU - Schmid, Ute AU - Zeller, Christina AU - Tamaddoni-Nezhad, Alireza AU - Besold, Tarek PY - 2018 JO - Machine Learning VL - 107 IS - 7 SP - 1119-1140 PB - Springer Science + Business Media B.V CY - Dordrecht [u.a.] SN - 1573-0565 DO - 10.1007/s10994-018-5707-3 UR - https://fis.uni-bamberg.de/handle/uniba/53455 LA - eng AB - During the 1980s Michie defined Machine Learning in terms of two orthogonal axes of performance: predictive accuracy and comprehensibility of generated hypotheses. Since predictive accuracy was readily measurable and comprehensibility not so, later definitions in the 1990s, such as Mitchell’s, tended to use a one-dimensional approach to Machine Learning based solely on predictive accuracy, ultimately favouring statistical over symbolic Machine Learning approaches. In this paper we provide a definition of comprehensibility of hypotheses which can be estimated using human participant trials. We present two sets of experiments testing human comprehensibility of logic programs. In the first experiment we test human comprehensibility with and without predicate invention. Results indicate comprehensibility is affected not only by the complexity of the presented program but also by the existence of anonymous predicate symbols. In the second experiment we directly test whether any state-of-the-art ILP systems are ultra-strong learners in Michie’s sense, and select the Metagol system for use in humans trials. Results show participants were not able to learn the relational concept on their own from a set of examples but they were able to apply the relational definition provided by the ILP system correctly. This implies the existence of a class of relational concepts which are hard to acquire for humans, though easy to understand given an abstract explanation. We believe improved understanding of this class could have potential relevance to contexts involving human learning, teaching and verbal interaction. KW - Inductive logic programming KW - Comprehensibility KW - ultra-strong machine learning ER - TY - JOUR TI - Keep IT Going, Girl! : An Empirical Analysis of Gendered Career Chances and Career Aspirations Among German Graduates in Computer Sciences AU - Förtsch, Silvia AU - Gärtig-Daugs, Anja AU - Buchholz, Sandra AU - Schmid, Ute PY - 2018 JO - International Journal of Gender, Science and Technology VL - 10 IS - 2 SP - 265-286 PB - Open Univ. CY - Milton Keynes SN - 2040-0748 UR - https://fis.uni-bamberg.de/handle/uniba/47989 LA - eng ER - TY - JOUR TI - Notwendigkeit der Integration elementarinformatischer Lerneinheiten in den Vor- und Grundschulunterricht AU - Schmid, Ute AU - Gärtig-Daugs, Anja PY - 2018 JO - MedienPädagogik : Zeitschrift für Theorie und Praxis der Medienbildung IS - 31 SP - 78-106 CY - Zürich SN - 1424-3636 DO - 10.21240/mpaed/31/2018.03.29.X UR - https://fis.uni-bamberg.de/handle/uniba/47985 LA - deu ER - TY - JOUR TI - Informatik in der Grundschule AU - Schmid, Ute AU - Weitz, Katharina AU - Gärtig-Daugs, Anja PY - 2018 JO - Informatik-Spektrum : Organ der Gesellschaft für Informatik e.V. VL - 41 IS - 3 SP - 200-207 PB - Springer SN - 1432-122X DO - 10.1007/s00287-018-1103-4 UR - https://fis.uni-bamberg.de/handle/uniba/47984 LA - deu ER - TY - CPAPER TI - Forget it – delete it? Das Löschen von Informationen im Arbeitsalltag AU - Niessen, Cornelia AU - Göbel, Kyra AU - Siebers, Michael AU - Schmid, Ute PY - 2018 T2 - 51. Kongress der Deutschen Gesellschaft für Psychologie : Supplement to Psychological Test and Assessment Modeling 15. bis 20. September 2018 SP - 40 PB - Pabst Science Publishers CY - Lengerich, Westf SN - 978-3-95853-438-4 UR - https://fis.uni-bamberg.de/handle/uniba/46648 LA - deu ER - TY - CHAP TI - Was the Year 2000 a Leap Year? Step-wise Narrowing Theories with Metagol AU - Siebers, Michael AU - Schmid, Ute PY - 2018 T2 - Inductive logic programming : 28th International Conference, ILP 2018, Ferrara, Italy, September 2–4, 2018 : proceedings SP - 141-156 PB - Springer CY - Cham SN - 978-3-319-99960-9 UR - https://fis.uni-bamberg.de/handle/uniba/46919 LA - eng ER - TY - CHAP TI - Intentional Forgetting in Artificial Intelligence Systems: Perspectives and Challenges AU - Timm, Ingo J. AU - Staab, Steffen AU - Siebers, Michael AU - Schon, Claudia AU - Schmid, Ute AU - Sauerwald, Kai AU - Reuter, Lukas AU - Ragni, Marco AU - Niederée, Claudia AU - Maus, Heiko AU - Kern-Isberner, Gabriele AU - Jilek, Christian AU - Friemann, Paulina AU - Eiter, Thomas AU - Dengel, Andreas AU - Dames, Hannah AU - Bock, Tanja AU - Berndt, Jan Ole AU - Beierle, Christoph PY - 2018 T2 - KI 2018: advances in artificial intelligence : 41st German Conference on AI, Berlin, Germany, September 24-28, 2018 : proceedings SP - 357-365 PB - Springer CY - Cham SN - 978-3-030-00110-0 DO - 10.1007/978-3-030-00111-7_30 UR - https://fis.uni-bamberg.de/handle/uniba/46789 LA - eng ER - TY - CPAPER TI - Explaining Black-Box Classifiers with ILP – Empowering LIME with Aleph to Approximate Non-linear Decisions with Relational Rules AU - Rabold, Johannes Markus AU - Siebers, Michael AU - Schmid, Ute PY - 2018 T2 - Inductive Logic Programming : 28th International Conference, ILP 2018, Ferrara, Italy, September 2–4, 2018, Revised Selected Papers SP - 105-117 PB - Springer International Publishing CY - Cham SN - 978-3-319-99959-3 DO - 10.1007/978-3-319-99960-9_7 UR - https://fis.uni-bamberg.de/handle/uniba/46526 LA - eng ER - TY - CHAP TI - Comparing Automated Pain Classifiers with Human Performance AU - Folger, Johannes AU - Siebers, Michael AU - Kunz, Miriam AU - Lautenbacher, Stefan AU - Schmid, Ute PY - 2018 PB - opus CY - Bamberg DO - 10.20378/irbo-51771 UR - https://fis.uni-bamberg.de/handle/uniba/43676 LA - deu ER - TY - CPAPER TI - Modelling Adaptation Effects as Similarity to Dynamic Prototypes AU - Siebers, Michael AU - Folger, Johannes AU - Schineller, Simone AU - Seuß, Dominik AU - Faerber, Stella AU - Schmid, Ute PY - 2018 PB - opus CY - Bamberg DO - 10.20378/irbo-51775 UR - https://fis.uni-bamberg.de/handle/uniba/43681 LA - deu ER - TY - CHAP TI - Implicit and Explicit Learning of Artificial Grammars from Letter Strings, Visual, and Visual-Motor Patterns AU - Hofmann, Jacqueline AU - Kaiser, Tobias AU - Schmid, Ute PY - 2018 PB - opus CY - Bamberg DO - 10.20378/irbo-51772 UR - https://fis.uni-bamberg.de/handle/uniba/43649 LA - deu ER - TY - CPAPER TI - Does Artificial Intelligence Exist? No, it doesnt! AU - Dörner, Dietrich ED - Schmid, Ute ED - Siebers, Michael ED - Carbon, Claus-Christian ED - Raab, Marius ED - Rüsseler, Jascha ED - Gross, Tom ED - Schlieder, Christoph ED - Dörner, Dietrich PY - 2018 T2 - Proceedings of KogWis 2012. 11th Biannual Conference of the German Cognitive Science Society PB - University of Bamberg Press CY - Bamberg T3 - Schriften aus der Fakultät Wirtschaftsinformatik und Angewandte Informatik der Otto-Friedrich-Universität Bamberg SN - 978-3-86309-100-2 UR - https://fis.uni-bamberg.de/handle/uniba/1955 LA - eng ER - TY - CPAPER TI - Mental Models, Career Aspirations, and the Acquirement of Basic Concepts of Computer Science in Elementary Education AU - Wolking, Maike AU - Schmid, Ute PY - 2017 T2 - Proceedings of the 12th Workshop on Primary and Secondary Computing Education SP - 119-120 PB - ACM CY - New York,NY,United States SN - 978-1-4503-5428-8 DO - 10.1145/3137065.3137076 UR - https://fis.uni-bamberg.de/handle/uniba/95384 LA - eng ER - TY - JOUR TI - Living Lab Bamberg : an infrastructure to explore smart city research challenges in the wild AU - Benabbas, Aboubakr AU - Elmamooz, Golnaz AU - Lagesse, Brent AU - Nicklas, Daniela AU - Schmid, Ute PY - 2017 JO - Künstliche Intelligenz : KI ; Forschung, Entwicklung, Erfahrungen VL - 31 IS - 3 SP - 265–271 PB - Springer CY - Berlin SN - 0933-1875 DO - 10.1007/s13218-017-0497-5 UR - https://fis.uni-bamberg.de/handle/uniba/50160 LA - eng ER - TY - CPAPER TI - Kindliche Modelle der digitalen Welt AU - Gärtig-Daugs, Anja AU - Weitz, Katharina AU - Schmid, Ute PY - 2017 T2 - Informatische Bildung zum Verstehen und Gestalten der digitalen Welt : 17. GI-Fachtagung Informatik und Schule vom 13.-15. September 2017 in Oldenburg SP - 419-420 CY - Bonn SN - 978-3-88579-668-8 UR - https://fis.uni-bamberg.de/handle/uniba/47987 LA - deu ER - TY - CPAPER TI - Computer Science in Early Childhood Education : Pedagogical Beliefs and Perceived Self-Confidence in Preschool Teachers AU - Weitz, Katharina AU - Gärtig-Daugs, Anja AU - Knauf, Daniel Siegfried AU - Schmid, Ute PY - 2017 T2 - WiPSCE '17: Proceedings of the 12th Workshop on Primary and Secondary Computing Education SP - 117-118 PB - ACM Press CY - New York SN - 978-1-4503-5428-8 DO - 10.1145/3137065.3144573 UR - https://fis.uni-bamberg.de/handle/uniba/47986 LA - eng ER - TY - CPAPER TI - Requirements for a Companion System to Support Identifying Irrelevancy AU - Siebers, Michael AU - Göbel, Kyra AU - Niessen, Cornelia AU - Schmid, Ute PY - 2017 T2 - 2017 International Conference on Companion Technology (ICCT) PB - IEEE DO - 10.1109/COMPANION.2017.8287076 UR - https://fis.uni-bamberg.de/handle/uniba/44317 LA - eng AB - Though forgetting seems to be an everyday hassle, forgetting information not needed in the current context is helpful, even necessary. Such unneeded information is irrelevant to your current task at best, and at worst, deteriorates performance. For example, when writing a computer program in C#, you should temporarily forget your Java knowledge, since these programming languages are similar but not quite the same. Bjork, Bjork, and Anderson summarize this type of forgetting under the term goal-directed forgetting. ER - TY - CPAPER TI - Computer models solving intelligence test problems: progress and implications (Extended Abstract) AU - Hernández-Orallo, José AU - Martínez-Plumed, Fernando AU - Schmid, Ute AU - Siebers, Michael AU - Dowe, David PY - 2017 T2 - Proceedings of the Twenty-Sixth International Joint Conference on Artificial Intelligence SP - 5005-5009 DO - 10.24963/ijcai.2017/711 UR - https://fis.uni-bamberg.de/handle/uniba/44275 LA - eng ER - TY - CPAPER TI - Intentionales Vergessen im Arbeitsalltag : Eine Critical Incident Untersuchung AU - Niessen, Cornelia AU - Göbel, Kyra AU - Siebers, Michael AU - Schmid, Ute ED - Wegge, Jürgen ED - Helmert, Jens R. ED - Kruse, Philipp ED - Pannasch, Sebastian PY - 2017 T2 - 10. Tagung der Fachgruppe Arbeits-, Organisations- und Wirtschaftspsychologie der Deutschen Gesellschaft für Psychologie "Human Performance in Socio-Technical Systems" : Program SP - 363 CY - Berlin UR - https://fis.uni-bamberg.de/handle/uniba/44276 LA - deu ER - TY - JOUR TI - A Psychonic Approach to the Design of a Cognitive Companion Supporting Intentional Forgetting AU - Siebers, Michael AU - Schmid, Ute AU - Göbel, Kyra AU - Niessen, Cornelia PY - 2017 JO - Kognitive Systeme IS - 1 PB - DuEPublico CY - Duisburg ; Essen SN - 2197-0343 DO - 10.17185/duepublico/44537 UR - https://fis.uni-bamberg.de/handle/uniba/44268 LA - eng AB - We present the design basics of the cognitive companion Dare2Del which supports humans to temporarily ignore or permanently forget digital objects. The system infers the irrelevancy of digital objects based on a symbolic knowledge representation and white box machine learning. The logic-like knowledge base of the system is split in facts that apply to individual digital objects (data) and general rules which hold for all objects in the domain (domain theory). The irrelevancy of digital objects is inferred using explicit rules, which are learned by an inductive logic programming approach. In this paper, we focus on the knowledge base and the inference for the permanent deletion of files. First, we present relations available for data and domain theory. Then, we evaluate whether the chosen relations are suitable for inferring the irrelevancy of files. We evaluate a handcrafted irrelevancy rule on an artificial file system with 500 files. For that, we developed a generator for knowledge bases of artificial file systems. We were able to classify 97.2% of the files correctly as irrelevant or relevant. ER - TY - BOOK TI - Referate präsentieren mit PowerPoint für Dummies Junior AU - Schmid, Ute AU - Weitz, Katharina PY - 2017 PB - Wiley CY - Weinheim SN - 978-3-527-71396-7 UR - https://fis.uni-bamberg.de/handle/uniba/42710 LA - deu ER - TY - RPRT TI - Unternehmenskulturen im Wandel - Karriereentwicklung im Informatikbereich. Ergebnisse des Forschungsprojektes "Alumnae Tracking" AU - Förtsch, Silvia AU - Gärtig-Daugs, Anja AU - Schmid, Ute PY - 2017 PB - opus CY - Bamberg UR - https://fis.uni-bamberg.de/handle/uniba/42406 LA - deu AB - Unternehmenskulturen im Wandel beinhaltet quantitative Ergebnisse aus der Studierenden- und Ehemaligenbefragung sowie qualitative Ergebnisse aus der Unternehmensbefragung im Forschungsprojekt "Alumnae Tracking". ER - TY - RPRT TI - Zehn Jahre Elementarinformatik : Elementare Informatikkompetenzen als Basis für nicht-konsumierenden und reflektierten Umgang mit Computer-Medien in der Vor- und Grundschule, 2008-2017 AU - Schmid, Ute AU - Gärtig-Daugs, Anja PY - 2017 PB - opus CY - Bamberg T3 - Werkstattberichte zur Elementarinformatik UR - https://fis.uni-bamberg.de/handle/uniba/42259 LA - deu AB - Ausgangspunkt unseres didaktischen Ansatzes ist die Forderung, dass im Vor- und Grundschulbereich Mediennutzung und Vermittlung von elementaren Informatikkonzepten wechselseitig aufeinander bezogen werden sollten. Bei einer Vermittlung von Informatikkonzepten ohne Bezug zum Computer, wird es Kindern nicht gelingen, die Beziehung selbständig herzustellen. Es ist aber davon auszugehen, dass erst das explizite Inbeziehungsetzen Kinder anregen kann, auch weiterführende „Wie funktioniert das?“ Fragen zu stellen und damit erste Schritte in Richtung eines konstruktiven Lernens von Informatikinhalten zu gehen. Umgekehrt sind Kinder hochmotiviert, Computermedien zu nutzen. Allerdings werden diese im Alltag häufig rein konsumierend eingesetzt. Computer werden als Unterhaltungsmedium, ähnlich dem Fernseher, wahrgenommen. Malprogramme und visuelle Programmiersprachen wie ScratchJr können genutzt werden, um Kindern den Computer als Medium nahezubringen, mit dem man kreativ gestalten kann. Für eine gelingende Integration elementarinformatischer Inhalte ist es notwendig, Unterrichtseinheiten anzubieten, die in verschiedenen Fachzusammenhängen – Deutsch, Kunst, Sachunterricht, Mathematik – eingebracht und die problemlos von nicht vorgebildetem Personal eingesetzt werden können. Im vorliegenden Werkstattbericht werden die grundlegenden Konzepte unseres Ansatzes motiviert, die Lehreinheiten vorgestellt, Integrationsmöglichkeiten in verschiedene Unterrichtsfächer aufgezeigt und ein Erfahrungsbericht aus den ersten durchgeführten Workshops gegeben. KW - Elementarinformatik KW - Medienkompetenz KW - Informatikkompetenz KW - Montessori-Pädagogik KW - Vorschule, Grundschule ER - TY - CPAPER TI - Automatic Generation of Analogous Problems for Written Subtraction AU - Zeller, Christina AU - Schmid, Ute ED - Reitter, David ED - Ritter, Frank E. PY - 2017 PB - opus CY - Bamberg UR - https://fis.uni-bamberg.de/handle/uniba/41883 LA - eng AB - - KW - analogy, intelligent tutor systems, written subtraction ER - TY - CPAPER TI - Automatic Generation of Analogous Problems to Help Resolving Misconceptions in an Intelligent Tutor System for Written Subtraction AU - Zeller, Christina AU - Schmid, Ute PY - 2017 PB - opus CY - Bamberg UR - https://fis.uni-bamberg.de/handle/uniba/41882 LA - eng AB - In domains involving procedural skills such as mathematics or programming, students often are prone to misconceptions which result in erroneous solutions. We present the ASG algorithm for generation of analogous problems of written subtraction as an extension of an intelligent tutor system (ITS) proposed by Zinn (2014). The student module of this ITS does not rely on an error library but uses algorithmic de-bugging where an erroneous solution is recognized by identifying which expert rules fail when trying to reproduce the student solution. Since the ITS allows students to create their own subtraction problems, feedback generation must be online and automatic. ASG is a constraint-based algorithm for constructing problems which are structurally isomorphic to the current, erroneously solved student problem. KW - analogy, intelligent tutor systems, written subtraction ER - TY - JOUR TI - Problems of video-based pain detection in patients with dementia : a road map to an interdisciplinary solution AU - Seuß, Dominik AU - Hassan, Teena AU - Garbas, Jens AU - Siebers, Michael AU - Schmid, Ute AU - Schöberl, Michael AU - Lautenbacher, Stefan AU - Kunz, Miriam PY - 2017 PB - opus CY - Bamberg UR - https://fis.uni-bamberg.de/handle/uniba/41854 LA - eng AB - Background Given the unreliable self-report in patients with dementia, pain assessment should also rely on the observation of pain behaviors, such as facial expressions. Ideal observers should be well trained and should observe the patient continuously in order to pick up any pain-indicative behavior; which are requisitions beyond realistic possibilities of pain care. Therefore, the need for video-based pain detection systems has been repeatedly voiced. Such systems would allow for constant monitoring of pain behaviors and thereby allow for a timely adjustment of pain management in these fragile patients, who are often undertreated for pain. Methods In this road map paper we describe an interdisciplinary approach to develop such a video-based pain detection system. The development starts with the selection of appropriate video material of people in pain as well as the development of technical methods to capture their faces. Furthermore, single facial motions are automatically extracted according to an international coding system. Computer algorithms are trained to detect the combination and timing of those motions, which are pain-indicative. Results/conclusion We hope to encourage colleagues to join forces and to inform end-users about an imminent solution of a pressing pain-care problem. For the near future, implementation of such systems can be foreseen to monitor immobile patients in intensive and postoperative care situations. ER - TY - JOUR TI - Problems of video-based pain detection in patients with dementia : a road map to an interdisciplinary solution AU - Seuß, Dominik AU - Hassan, Teena AU - Kunz, Miriam AU - Garbas, Jens U. AU - Siebers, Michael AU - Schmid, Ute AU - Schöberl, Michael AU - Lautenbacher, Stefan PY - 2017 JO - BMC Geriatrics VL - 17 IS - 1 PB - BioMed Central CY - London SN - 1471-2318 DO - 10.1186/s12877-017-0427-2 UR - https://fis.uni-bamberg.de/handle/uniba/41844 LA - eng AB - Given the unreliable self-report in patients with dementia, pain assessment should also rely on the observation of pain behaviors, such as facial expressions. Ideal observers should be well trained and should observe the patient continuously in order to pick up any pain-indicative behavior; which are requisitions beyond realistic possibilities of pain care. Therefore, the need for video-based pain detection systems has been repeatedly voiced. Such systems would allow for constant monitoring of pain behaviors and thereby allow for a timely adjustment of pain management in these fragile patients, who are often undertreated for pain. KW - Facial expression KW - Automatic pain detection KW - Pain diagnostics KW - Dementia ER - TY - CPAPER TI - Automatic Generation of Analogous Problems for Written Subtraction AU - Zeller, Christina AU - Schmid, Ute PY - 2016 T2 - Proceedings of the 14th International Conference on Cognitive Modeling (ICCM 2016) SP - 241-242 UR - https://fis.uni-bamberg.de/handle/uniba/111039 LA - eng AB - - KW - analogy, intelligent tutor systems, written subtraction ER - TY - CPAPER TI - Automatic Generation of Analogous Problems to Help Resolving Misconceptions in an Intelligent Tutor System for Written Subtraction AU - Zeller, Christina AU - Schmid, Ute PY - 2016 T2 - Workshops Proceedings for the Twenty-fourth International Conference on Case-Based Reasoning (ICCBR 2016) SP - 108-117 UR - https://fis.uni-bamberg.de/handle/uniba/111038 LA - eng AB - In domains involving procedural skills such as mathematics or programming, students often are prone to misconceptions which result in erroneous solutions. We present the ASG algorithm for generation of analogous problems of written subtraction as an extension of an intelligent tutor system (ITS) proposed by Zinn (2014). The student module of this ITS does not rely on an error library but uses algorithmic de-bugging where an erroneous solution is recognized by identifying which expert rules fail when trying to reproduce the student solution. Since the ITS allows students to create their own subtraction problems, feedback generation must be online and automatic. ASG is a constraint-based algorithm for constructing problems which are structurally isomorphic to the current, erroneously solved student problem. KW - analogy, intelligent tutor systems, written subtraction ER - TY - CPAPER TI - Gemeinsame mentale Modelle in der agilen Softwareentwicklung : Ein Ansatz zur Erstellung von Gestaltungsempfehlungen für “gute” erfahrungsspezifische User Stories. AU - Hallmann, Daniel AU - Schmid, Ute AU - Weth, Rüdiger von der PY - 2016 T2 - Informatik 2016 : Tagung vom 26. - 30. September 2016 in Klagenfurt SP - 1969-1974 PB - Gesellschaft für Informatik e.V. CY - Bonn SN - 978-3-88579-653-4 UR - https://fis.uni-bamberg.de/handle/uniba/48190 LA - deu AB - User Stories sind ein probates Mittel zum Austausch von Anforderungen in der agilen Softwareentwicklung. Die Anwendung ist jedoch kritisch, da sich immer wieder Fehler in der Beschreibung einzelner Formularfelder wie den Akzeptanzkriterien einschleichen. Mit diesen fehlerhaften User Stories müssen Personen mit individuellen Erfahrungen ein gemeinsames mentales Modell konstruieren. Häufig ist der Aufbau jedoch nicht möglich und es kommt zu negativen Reaktionen wie Frustration bei fehlenden Erfahrungen, langen Diskussionen bei unterschiedlichen Vorstellungen und teuren Nacharbeiten bei missverstandenen Inhalten. Aufgrund dieser Effekte sollen mit einer Ex-post-Analyse, einer Feldstudie und einem Experiment die Zusammenhänge von fehlerhaften User Stories, individuellen Erfahrungen und gemeinsamen mentalen Modellen untersucht werden. Mit dieser Sicht auf die Verarbeitung von User Stories wird das Forschungsinteresse für kognitionspsychologische Prozesse in der agilen Softwareentwicklung unterstützt. Außerdem liefert die Arbeit für die Praxis Gestaltungsempfehlungen für „gute“ erfahrungsspezifische User Stories. Mit dieser Strategie sollen frühzeitig die Kosten in der agilen Softwareentwicklung reduziert werden. KW - Agile Softwareentwicklung KW - Qualität von User Stories KW - Kognitive Psychologie KW - Erfahrungen KW - Gemeinsame Mentale Modelle ER - TY - CPAPER TI - Automatische Detektion von Trockenstress bei Tabakpflanzen mittels Machine-Learning-Verfahren AU - Siebers, Michael AU - Uhrmann, Franz AU - Scholz, Oliver AU - Stocker, Christoph AU - Schmid, Ute ED - Ruckelshausen, Arno ED - Meyer-Aurich, Andreas ED - Rath, Thomas ED - Recke, Guido ED - Theuvsen, Brigitte PY - 2016 T2 - Informatik in der Land-, Forst- und Ernährungswirtschaft Fokus : Intelligente Systeme - Stand der Technik und neue Möglichkeiten : Referate der 36. GIL-Jahrestagung, 22.-23. Februar 2016 in Osnabrück, Germany SP - 197-200 PB - Köllen Druck+Verlag GmbH CY - Bonn T3 - GI-Edition Lecture notes in informatics. Proceedings SN - 978-3-88579-647-3 UR - https://fis.uni-bamberg.de/handle/uniba/41745 LA - deu AB - Dieser Beitrag befasst sich mit der Klassifikation der Vitalität von Pflanzen durch Machine-Learning-Verfahren am Beispiel von Trockenstress bei Tabak (Nicotiana tabacum). Wir zeigen, dass Machine-Learning-Verfahren die menschliche Unterscheidung von gesunden und gestressten Pflanzen durch einen Experten nachbilden können und zudem, dass eine frühzeitige Erkennung von Pflanzenstress möglich ist, indem eine dritte Klasse für mäßig gestresste Pflanzen eingeführt wird. Zur Klassifikation werden Entscheidungsbaumverfahren, Support Vector Machine, künstliche Neuronale Netze und Lineare Regression verglichen. Im Beitrag wird schwerpunktmäßig die Auswahl der Merkmale beschrieben, die für eine zuverlässige Klassifikation notwendig sind. Da die Experteneinschätzung weniger auf Einzelkriterien als vielmehr auf dem Gesamteindruck des Pflanzenphänotyps basiert, stellt sich die Frage, welche relevanten Merkmale ein automatisches Diagnose-System berücksichtigen muss. Es hat sich herausgestellt, dass neben blattspezifischen Merkmalen auch Merkmale, die sich auf die Gesamtpflanze beziehen, für die Klassifikation relevant sind. KW - Phänotypisierung KW - Trockenstress KW - Machine-Learning KW - Klassifikation KW - Merkmale ER - TY - CPAPER TI - A Practical Approach to Fuse Shape and Appearance Information in a Gaussian Facial Action Estimation Framework AU - Hassan, Teena AU - Seuß, Dominik AU - Wollenberg, Johannes AU - Garbas, Jens AU - Schmid, Ute PY - 2016 T2 - Proceedings : ECAI 2016 SP - 1812-1817 PB - IOS Press CY - Amsterdam T3 - Frontiers in Artificial Intelligence and Applications DO - 10.3233/978-1-61499-672-9-1812 UR - https://fis.uni-bamberg.de/handle/uniba/40994 LA - eng ER - TY - CPAPER TI - Computer science experimenter's kit for use in preschool and primary school AU - Gärtig-Daugs, Anja AU - Weitz, Katharina AU - Wolking, Maike AU - Schmid, Ute PY - 2016 T2 - Proceedings of the 11th Workshop in Primary and Secondary Computing Education SP - 66-71 PB - ACM CY - New York, NY, USA SN - 978-1-4503-4223-0 DO - 10.1145/2978249.2978258 UR - https://fis.uni-bamberg.de/handle/uniba/40948 LA - eng ER - TY - JOUR TI - Why Generality Is Key to Human-Level Artificial Intelligence AU - Besold, Tarek AU - Schmid, Ute PY - 2016 JO - Advances in Cognitive Systems VL - 4 SP - 13-24 SN - 2324-8416 UR - https://fis.uni-bamberg.de/handle/uniba/40946 LA - eng ER - TY - JOUR TI - Computer models solving intelligence test problems: Progress and implications AU - Hernández-Orallo, José AU - Martínez-Plumed, Fernando AU - Schmid, Ute AU - Siebers, Michael AU - Dowe, David L. PY - 2016 JO - Artificial Intelligence IS - 230 SP - 74-107 PB - Elsevier CY - Amsterdam SN - 0004-3702 DO - 10.1016/j.artint.2015.09.011 UR - https://fis.uni-bamberg.de/handle/uniba/39916 LA - eng AB - While some computational models of intelligence test problems were proposed throughout the second half of the XXth century, in the first years of the XXIst century we have seen an increasing number of computer systems being able to score well on particular intelligence test tasks. However, despite this increasing trend there has been no general account of all these works in terms of how they relate to each other and what their real achievements are. Also, there is poor understanding about what intelligence tests measure in machines, whether they are useful to evaluate AI systems, whether they are really challenging problems, and whether they are useful to understand (human) intelligence. In this paper, we provide some insight on these issues, in the form of nine specific questions, by giving a comprehensive account of about thirty computer models, from the 1960s to nowadays, and their relationships, focussing on the range of intelligence test tasks they address, the purpose of the models, how general or specialised these models are, the AI techniques they use in each case, their comparison with human performance, and their evaluation of item difficulty. As a conclusion, these tests and the computer models attempting them show that AI is still lacking general techniques to deal with a variety of problems at the same time. Nonetheless, a renewed attention on these problems and a more careful understanding of what intelligence tests offer for AI may help build new bridges between psychometrics, cognitive science, and AI; and may motivate new kinds of problem repositories. KW - Intelligence tests KW - Cognitive models KW - Artificial intelligence KW - Intelligence evaluation ER - TY - JOUR TI - Characterizing facial expressions by grammars of action unit sequences - A first investigation using ABL AU - Siebers, Michael AU - Schmid, Ute AU - Seuß, Dominik AU - Kunz, Miriam AU - Lautenbacher, Stefan PY - 2016 JO - Information sciences : an international journal IS - 329 Special Issue on Discovery Science SP - 866-875 PB - Elsevier Science Inc. CY - New York, NY SN - 0020-0255 DO - 10.1016/j.ins.2015.10.007 UR - https://fis.uni-bamberg.de/handle/uniba/39900 LA - eng AB - We investigate the application of grammar inference to the analysis of facial expressions to discover underlying sequential regularities characteristic for a specific mental state. The input consists of sequences of action units (AUs), which represent basic facial signals. The typical classification task for facial expression analysis is to assign a set of AUs its corresponding mental state, e.g., an emotion. To our knowledge, there is no research investigating whether there is diagnostic information in the sequence in which the AUs occur in a given time interval. Our study is based on data of facial expressions of pain obtained in a psychological experiment with 347 pain episodes of 86 subjects represented as sequences of AUs. We applied the Alignment-Based Learning (ABL) approach to infer the underlying grammar for the set of all AUs which occurred in the sequences and for a reduced alphabet of the relevant AUs only. We used 10-fold cross-validation to estimate performance and we extended ABL with a frequency-based heuristics to reduce the number of grammar rules by eliminating such rules which do not contribute significantly to performance. The resulting grammar for the reduced AU alphabet provides a first approximation for a “grammar of pain”. KW - Grammar of pain KW - Alignment-Based Learning KW - Heuristic rule extraction KW - Facial expression analysis ER - TY - JOUR TI - Approaches and Applications of Inductive Programming AU - Hernández-Orallo, José AU - Muggleton, Stephen H. AU - Schmid, Ute AU - Zorn, Benjamin PY - 2015 JO - Dagstuhl Reports : Dokumentationen zu Dagstuhl-Seminaren und Dagstuhl-Perspektiven-Workshops VL - 5 IS - 10, Seminar 15442 SP - 89-111 CY - Wadern SN - 2192-5283 UR - https://fis.uni-bamberg.de/handle/uniba/40940 LA - eng ER - TY - CPAPER TI - Inductive Programming Meets the Real World AU - Gulwani, Sumit AU - Hernández-Orallo, Jose AU - Kitzelmann, Emanuel AU - Muggleton, Stephen H. AU - Schmid, Ute AU - Zorn, Benjamin PY - 2015 IS - 58 (2015), 11 SP - 90-99 PB - ACM CY - New York, NY DO - 10.1145/2736282 UR - https://fis.uni-bamberg.de/handle/uniba/40061 LA - eng ER - TY - JOUR TI - Can machine intelligence be measured in the same way as human intelligence AU - Besold, Tarek AU - Schmid, Ute AU - Hernández-Orallo, José PY - 2015 JO - Künstliche Intelligenz : KI ; Forschung, Entwicklung, Erfahrungen ; Organ des Fachbereichs 1 Künstliche Intelligenz der Gesellschaft für Informatik e.V., GI VL - 29 IS - 3 SP - 291-297 PB - Springer CY - Berlin ; Heidelberg [u.a.] SN - 0933-1875 DO - 10.1007/s13218-015-0361-4 UR - https://fis.uni-bamberg.de/handle/uniba/40022 LA - eng ER - TY - JOUR TI - Don Giovanni ist kein Rückschlagspiel - Wie Wikipedia helfen kann Freitexte zu vergleichen. AU - Schmid, Ute PY - 2015 JO - Uni.vers : das Magazin der Otto-Friedrich-Universität Bamberg IS - 21, Ein Universum des Wissens für alle - Bamberger Perspektiven auf die Wikipedia SP - 50-53 CY - Bamberg SN - 1618-9019 UR - https://fis.uni-bamberg.de/handle/uniba/40016 LA - deu ER - TY - JOUR TI - Introvertierte Studenten, fleißige Studentinnen? : Geschlechtsspezifische Unterschiede in Motivation, Zufriedenheit und Wahrnehmungsmustern bei Informatikstudierenden AU - Schmid, Ute AU - Förtsch, Silvia AU - Gärtig-Daugs, Anja PY - 2015 JO - Informatik-Spektrum : Organ der Gesellschaft für Informatik e.V. und mit ihr assoziierter Organisationen VL - 38 IS - 5 SP - 379-395 PB - Springer CY - Berlin ; Heidelberg [u.a.] SN - 0170-6012 DO - 10.1007/s00287-014-0784-6 UR - https://fis.uni-bamberg.de/handle/uniba/40026 LA - deu ER - TY - JOUR TI - Neigung entdecken, Informatik studieren, als Informatikerin arbeiten : Vernetzung von Maßnahmen und Begleitforschung an einem Standort AU - Schmid, Ute AU - Gärtig-Daugs, Anja AU - Förtsch, Silvia PY - 2015 JO - Frauen machen Informatik : Magazin der Fachgruppe Frauen und Informatik VL - 39 SP - 21-25 CY - Bonn SN - 2364-6152 UR - https://fis.uni-bamberg.de/handle/uniba/40015 LA - deu ER - TY - CPAPER TI - Comparing Computer Models Solving Number Series Problems AU - Schmid, Ute AU - Ragni, Marco ED - Bieger, Jordi ED - Goertzel, Ben ED - Potapov, Alexey PY - 2015 T2 - Artificial General Intelligence : 8th International Conference, AGI 2015, AGI 2015, Berlin, Germany, July 22-25, 2015, Proceedings SP - 352-361 PB - Springer CY - Berlin T3 - Lecture Notes in Computer Science SN - 978-3-319-21364-4 UR - https://fis.uni-bamberg.de/handle/uniba/40006 LA - eng ER - TY - CHAP TI - Modellierung psychischer Prozesse AU - Dörner, Dietrich AU - Schmid, Ute PY - 2015 T2 - Psychologie : Eine Einführung in ihre Grundlagen und Anwendungsfelder SP - 329-344 PB - Kohlhammer CY - Stuttgart ET - 5., überarb. u. erw. Aufl. SN - 978-3-17-026133-4 UR - https://fis.uni-bamberg.de/handle/uniba/21671 LA - deu ER - TY - BOOK TI - Psychologie : Eine Einführung in ihre Grundlagen und Anwendungsfelder AU - Schütz, Astrid AU - Brand, Matthias AU - Selg, Herbert AU - Lautenbacher, Stefan AU - Lück, Helmut E. AU - Hallschmid, Manfred AU - Born, Jan AU - Carbon, Claus-Christian AU - Schermer, Franz J. AU - Funke, Joachim AU - Wühr, Peter AU - Rothermund, Klaus AU - Brandstätter, Veronika AU - Achtziger, Anja AU - Gollwitzer, Peter AU - Weinert, Sabine AU - Laux, Lothar AU - Renner, Karl-Heinz AU - Walther, Eva AU - Weil, Rebecca AU - Renkewitz, Frank AU - Sedlmeier, Peter AU - Rentzsch, Katrin AU - Marcus, Bernd AU - Dörner, Dietrich AU - Schmid, Ute AU - Reinecker, Hans AU - Beesdo-Baum, Katja AU - Vollmann, Manja AU - Weber, Hannelore AU - Wiese, Bettina S. AU - Volmer, Judith AU - Spurk, Daniel AU - Moser, Klaus AU - Paul, Karsten I. AU - Gold, Andreas AU - Borsch, Frank AU - Ohler, Peter AU - Nieding, Gerhild AU - Sporer, Siegfried Ludwig AU - Breuer, Maike Miriam AU - Krems, Josef F. AU - Baumann, Martin AU - Plessner, Henning AU - Teubel, Thomas AU - Schäfer, Thomas AU - Lauenstein, Oliver AU - Güss, C. Dominik AU - Heydasch, Timo AU - Rudolph, Udo ED - Schütz, Astrid ED - Brand, Matthias ED - Selg, Herbert ED - Stefan, Lautenbacher PY - 2015 PB - Kohlhammer CY - Stuttgart ET - 5., überarb. u. erw. Aufl. SN - 978-3-17-026133-4 UR - https://fis.uni-bamberg.de/handle/uniba/21658 LA - deu ER - TY - JOUR TI - "Alumnae Tracking" Frauenkarrieren in der Informatik AU - Gärtig-Daugs, Anja AU - Förtsch, Silvia AU - Schmid, Ute PY - 2014 JO - FifF - Kommunikation VL - 11 IS - 3 SP - 30-37 PB - FIfF-Geschäftsstelle CY - Bremen UR - https://fis.uni-bamberg.de/handle/uniba/21031 LA - deu ER - TY - CPAPER TI - Applying Inductive Program Synthesis to Induction of Number Series A Case Study with IGOR2 AU - Hofmann, Jacqueline AU - Kitzelmann, Emanuel AU - Schmid, Ute ED - Lutz, Carsten ED - Thielscher , Michael PY - 2014 T2 - KI 2014: Advances in Artificial Intelligence ; 37th Annual German Conference on AI, Stuttgart, Germany, September 22-26, 2014 ; Proceedings SP - 25-36 PB - Springer CY - Cham [u.a.] T3 - Lecture Notes in Computer Science SN - 978-3-319-11205-3 UR - https://fis.uni-bamberg.de/handle/uniba/21028 LA - eng ER - TY - CPAPER TI - The Use of Creative Analogies in a Complex Problem Situation : Abstract AU - Damaskinos, Melanie AU - Lutsevich, Alexander AU - Dörner, Dietrich AU - Schmid, Ute AU - Güss, C. Dominik PY - 2014 IS - 15 (2014), 1 Supplement, September 2014, 12th Biannual Conference of the German Cognitive Science Society (Gesellschaft für Kognitionswissenschaft) SP - S34-S35 PB - Springer CY - Heidelberg ; Berlin SN - 1612-4782 UR - https://fis.uni-bamberg.de/handle/uniba/21040 LA - eng ER - TY - CPAPER TI - LWA 2013 : Lernen, Wissen & Adaptivität ; Workshop Proceedings Bamberg, 7.-9. October 2013 AU - Bergner, Arndt AU - Schmid, Ute ED - Henrich, Andreas ED - Sperker, Hans-Christian PY - 2014 PB - opus CY - Bamberg UR - https://fis.uni-bamberg.de/handle/uniba/2837 LA - other AB - LWA Workshop Proceedings: LWA stands for "Lernen, Wissen, Adaption" (Learning, Knowledge, Adaptation). It is the joint forum of four special interest groups of the German Computer Science Society (GI). Following the tradition of the last years, LWA provides a joint forum for experienced and for young researchers, to bring insights to recent trends, technologies and applications, and to promote interaction among the SIGs. ER - TY - BOOK TI - Handbuch der Künstlichen Intelligenz AU - Schmid, Ute ED - Görz, Günther ED - Schneeberger, Josef ED - Schmid, Ute PY - 2013 PB - Oldenbourg CY - München ET - 5 SN - 978-3-486-71979-6 UR - https://fis.uni-bamberg.de/handle/uniba/2751 LA - deu ER - TY - CPAPER TI - On the Relevance of Sequence Information for Decoding Facial Expressions of Pain and Disgust? : An Avatar Study AU - Siebers, Michael AU - Engelbrecht, Tamara AU - Schmid, Ute ED - Reichardt, Dirk PY - 2013 T2 - 7 th Workshop Emotion & Computing: Current Research and Future Impact : Proceedings SP - 3-9 CY - Koblenz UR - https://fis.uni-bamberg.de/handle/uniba/2758 LA - deu ER - TY - CHAP TI - How similar is what I get to what I want : Matchmaking for Mobility Support AU - Schmid, Ute AU - Berle, Lukas AU - Munz, Michael AU - Stein, Klaus AU - Sticht, Martin PY - 2013 T2 - Computational Approaches to Analogical Reasoning : Current Trends SP - 263-287 PB - Springer CY - Berlin T3 - Studies in Computational Intelligence SN - 978-3642545153 UR - https://fis.uni-bamberg.de/handle/uniba/2734 LA - eng ER - TY - CHAP TI - Kreativität und Problemlösen AU - Schmid, Ute AU - Funke, Joachim PY - 2013 T2 - Handbuch Kognitionswissenschaft SP - 335-343 PB - Metzler CY - Stuttgart u.a. SN - 978-3-476-02331-5 UR - https://fis.uni-bamberg.de/handle/uniba/2737 LA - deu ER - TY - CPAPER TI - A machine learning approach to drought stress level classification of tobacco plants AU - Stocker, Christoph AU - Uhrmann, Franz AU - Scholz, Oliver AU - Hügel, C. AU - Rademacher, T. AU - Siebers, Michael AU - Schmid, Ute ED - Henrich, Andreas ED - Sperker, Hans-Christian PY - 2013 T2 - LWA 2013: Lernen, Wissen & Adaptivität Workshop Proceedings, Bamberg, 7.-9.Oktober 2013 SP - 174-178 PB - opus CY - Bamberg UR - https://fis.uni-bamberg.de/handle/uniba/2731 LA - eng ER - TY - CPAPER TI - Erkennung von Sequenzen mimischer Schmerzausdrücke durch genetische Programmierung AU - Stocker, Christoph AU - Siebers, Michael AU - Schmid, Ute ED - Henrich, Andreas ED - Sperker, Hans-Christian PY - 2013 SP - 117-120 PB - opus CY - Bamberg UR - https://fis.uni-bamberg.de/handle/uniba/2726 LA - deu ER - TY - CHAP TI - Künstliche-Intelligenz-Forschung AU - Schmid, Ute PY - 2013 T2 - Handbuch Kognitionswissenschaft SP - 44-47 PB - Metzler CY - Stuttgart u.a. SN - 978-3-476-02331-5 UR - https://fis.uni-bamberg.de/handle/uniba/2730 LA - deu ER - TY - JOUR TI - A cognitive model for predicting esthetical judgements as similarity to dynamic prototypes AU - Schmid, Ute AU - Siebers, Michael AU - Folger, Johannes AU - Schineller, Simone AU - Seuß, Dominik AU - Raab, Marius AU - Carbon, Claus-Christian AU - Faerber, Stella J. PY - 2013 VL - 24 IS - Special Issue on ICCM 2012 SP - 72-79 PB - Elsevier Science CY - Amsterdam [u.a.] DO - 10.1016/j.cogsys.2012.12.002 UR - https://fis.uni-bamberg.de/handle/uniba/2410 LA - eng AB - We present a framework for cognitive modeling of esthetic decision making based on dynamic prototypes. Starting point of our work is empirical evidence which shows that subjects’ initial ratings of attractiveness of objects can be influenced by adapting them to new, typically more innovative objects. The framework consists of three steps: (1) Estimating an initial prototype from the ratings, (2) adapting the prototype due to the impact of the new objects, and (3) predicting the attractiveness ratings for subsequently presented object by their similarity to the adapted prototype. The framework allows representation of prototypes and objects as feature vectors containing metrical or categorial attributes or as structural representations. Within the framework, a variety of similarity measures and similarity-torating mappings can be explored to gain more precise insight into the cognitive processes underlying esthetical appreciations. We instantiated the framework for a first set of data obtained in a psychological experiment. In this experiment subjects rated the attractiveness of an initial set of chairs which varied in length of the backrest and the saturation of the color. Subjects then were adapted to a new set of chairs with extreme values on both dimensions. Finally, subjects again rated the initial objects. The framework was instantiated with an e-function to model the non-linear effects of variations in length and saturation on the judgements. Although there were only 25 data points per subject, we got satisfying results in predicting the shift of esthetical judgements due to adaptation to novel stimuli. ER - TY - JOUR TI - Assistive Technology to Support the Mobility of Senior Citizens AU - Schlieder, Christoph AU - Schmid, Ute AU - Munz, Michael AU - Stein, Klaus PY - 2013 JO - Künstliche Intelligenz : KI ; Forschung, Entwicklung, Erfahrungen VL - 27 IS - 3 SP - 247-253 PB - Springer CY - Berlin [u.a.] SN - 0933-1875 DO - 10.1007/s13218-013-0254-3 UR - https://fis.uni-bamberg.de/handle/uniba/2110 LA - eng AB - Maintaining mobility despite the bodily, mental, or monetary challenges which often come along with advanced age is a relevant aspect of the quality of live. The collaborative research project EMN-Moves provides assistive technology for initiating and coordinating mobility support in residential districts. Mobility support is seen as a social task involving the interplay of housing societies, social organisations and residents of different age groups—with and without special needs. The project focuses on two aspects: (1) a Geo-Wiki for documenting temporary mobility barriers and for generating proposals for alternative routes, (2) a matchmaking service for bringing together (elderly) people who need support with volunteers. ER - TY - CHAP TI - From Streams of Observations to Knowledge-Level Productive Predictions AU - Wernsdorfer, Mark AU - Schmid, Ute PY - 2013 T2 - Human behavior recognition technologies : intelligent applications for monitoring and security SP - 268-281 PB - Information Science Reference CY - Hershey, PA SN - 978-1-466-63682-8 UR - https://fis.uni-bamberg.de/handle/uniba/1088 LA - eng ER - TY - CPAPER TI - Building a Hierarchy of Functional Representations for Domain-Independent Reinforcement Learning in Non-Markovian Environments AU - Wernsdorfer, Mark ED - Schmid, Ute ED - Siebers, Michael ED - Carbon, Claus-Christian ED - Raab, Marius ED - Rüsseler, Jascha ED - Gross, Tom ED - Schlieder, Christoph ED - Dörner, Dietrich PY - 2012 T2 - Proceedings of KogWis 2012. 11th Biannual Conference of the German Cognitive Science Society SP - 49-50 PB - University of Bamberg Press CY - Bamberg T3 - Schriften aus der Fakultät Wirtschaftsinformatik und Angewandte Informatik der Otto-Friedrich-Universität Bamberg SN - 978-3-86309-100-2 UR - https://fis.uni-bamberg.de/handle/uniba/1990 LA - eng ER - TY - CPAPER TI - Preface AU - Schmid, Ute AU - Siebers, Michael AU - Carbon, Claus-Christian AU - Raab, Marius AU - Rüsseler, Jascha AU - Gross, Tom AU - Schlieder, Christoph AU - Dörner, Dietrich ED - Schmid, Ute ED - Siebers, Michael ED - Carbon, Claus-Christian ED - Raab, Marius ED - Rüsseler, Jascha ED - Gross, Tom ED - Schlieder, Christoph ED - Dörner, Dietrich PY - 2012 T2 - Proceedings of KogWis 2012. 11th Biannual Conference of the German Cognitive Science Society SP - xv-xvi PB - University of Bamberg Press CY - Bamberg T3 - Schriften aus der Fakultät Wirtschaftsinformatik und Angewandte Informatik der Otto-Friedrich-Universität Bamberg SN - 978-3-86309-100-2 UR - https://fis.uni-bamberg.de/handle/uniba/1995 LA - eng ER - TY - CPAPER TI - An Analytical Framework for Place Research AU - Kremer, Dominik ED - Schmid, Ute ED - Siebers, Michael ED - Carbon, Claus-Christian ED - Raab, Marius ED - Rüsseler, Jascha ED - Gross, Tom ED - Schlieder, Christoph ED - Dörner, Dietrich PY - 2012 T2 - Proceedings of KogWis 2012. 11th Biannual Conference of the German Cognitive Science Society SP - 43-44 PB - University of Bamberg Press CY - Bamberg T3 - Schriften aus der Fakultät Wirtschaftsinformatik und Angewandte Informatik der Otto-Friedrich-Universität Bamberg SN - 978-3-86309-100-2 UR - https://fis.uni-bamberg.de/handle/uniba/1958 LA - eng ER - TY - CPAPER TI - Acknowledgements AU - Schmid, Ute ED - Schmid, Ute ED - Siebers, Michael ED - Carbon, Claus-Christian ED - Raab, Marius ED - Rüsseler, Jascha ED - Gross, Tom ED - Schlieder, Christoph ED - Dörner, Dietrich PY - 2012 T2 - Proceedings of KogWis 2012. 11th Biannual Conference of the German Cognitive Science Society SP - xvii-xviii PB - University of Bamberg Press CY - Bamberg T3 - Schriften aus der Fakultät Wirtschaftsinformatik und Angewandte Informatik der Otto-Friedrich-Universität Bamberg SN - 978-3-86309-100-2 UR - https://fis.uni-bamberg.de/handle/uniba/1950 LA - eng ER - TY - CPAPER TI - Modeling Motivational Dynamics with Psi/MicroPsi AU - Bach, Joscha AU - Dörner, Dietrich ED - Schmid, Ute ED - Siebers, Michael ED - Carbon, Claus-Christian ED - Raab, Marius ED - Rüsseler, Jascha ED - Gross, Tom ED - Schlieder, Christoph ED - Dörner, Dietrich PY - 2012 T2 - Proceedings of KogWis 2012. 11th Biannual Conference of the German Cognitive Science Society SP - 58 PB - University of Bamberg Press CY - Bamberg SN - 978-3-86309-100-2 UR - https://fis.uni-bamberg.de/handle/uniba/1947 LA - eng ER - TY - CPAPER TI - Back to the Roots: Measuring Motoric Correlates of Ur-Emotions AU - Shengelia, Nato AU - Carbon, Claus-Christian AU - Raab, Marius ED - Schmid, Ute ED - Siebers, Michael PY - 2012 T2 - Proceedings of KogWis 2012 : 11th Biannual Conference of the German Cognitive Science Society SP - 141-142 PB - University of Bamberg Press CY - Bamberg SN - 978-3-86309-100-2 UR - https://fis.uni-bamberg.de/handle/uniba/1904 LA - eng ER - TY - CPAPER TI - Size Matters! How Value Organizes Our Perception of Art AU - Jakesch, Martina AU - Ortlieb, Stefan AU - Raab, Marius AU - Carbon, Claus-Christian ED - Schmid, Ute ED - Siebers, Michael ED - Carbon, Claus-Christian ED - Raab, Marius ED - Rüsseler, Jascha ED - Gross, Tom ED - Schlieder, Christoph ED - Dörner, Dietrich PY - 2012 T2 - Proceedings of KogWis 2012. 11th Biannual Conference of the German Cognitive Science Society SP - 88-89 PB - University of Bamberg Press CY - Bamberg T3 - Schriften aus der Fakultät Wirtschaftsinformatik und Angewandte Informatik der Otto-Friedrich-Universität Bamberg SN - 978-3-86309-100-2 UR - https://fis.uni-bamberg.de/handle/uniba/1902 LA - eng ER - TY - CPAPER TI - Motion and Emotion: Using Kinect to Force Ideomotor Empathy AU - Hesslinger, Vera AU - Muth, Claudia AU - Enz, Sibylle AU - Raab, Marius ED - Schmid, Ute ED - Siebers, Michael PY - 2012 T2 - Proceedings of KogWis 2012 : 11th Biannual Conference of the German Cognitive Science Society SP - 98-99 PB - University of Bamberg Press CY - Bamberg SN - 978-3-86309-100-2 UR - https://fis.uni-bamberg.de/handle/uniba/1889 LA - eng ER - TY - CPAPER TI - PsiCasso: Simulating the Dynamics of Aesthetic Appreciation AU - Imhof, Mike AU - Raab, Marius AU - Carbon, Claus-Christian ED - Schmid, Ute ED - Siebers, Michael PY - 2012 T2 - Proceedings of KogWis 2012 : 11th Biannual Conference of the German Cognitive Science Society SP - 129-131 PB - University of Bamberg Press CY - Bamberg SN - 978-3-86309-100-2 UR - https://fis.uni-bamberg.de/handle/uniba/1894 LA - eng ER - TY - CPAPER TI - Neuronale Veränderungen durch Schriftspracherwerb im Erwachsenenalter AU - Boltzmann, Melanie AU - Rüsseler, Jascha ED - Schmid, Ute ED - Siebers, Michael ED - Carbon, Claus-Christian ED - Raab, Marius ED - Rüsseler, Jascha ED - Gross, Tom ED - Schlieder, Christoph ED - Dörner, Dietrich PY - 2012 T2 - Proceedings of KogWis 2012. 11th Biannual Conference of the German Cognitive Science Society SP - 119-120 PB - University of Bamberg Press CY - Bamberg T3 - Schriften aus der Fakultät Wirtschaftsinformatik und Angewandte Informatik der Otto-Friedrich-Universität Bamberg SN - 978-3-86309-100-2 UR - https://fis.uni-bamberg.de/handle/uniba/1880 LA - deu ER - TY - CPAPER TI - Human-Computer Interaction: Concept, Methods, Tools AU - Gross, Tom AU - Beckmann, Christoph ED - Schmid, Ute ED - Siebers, Michael ED - Carbon, Claus-Christian ED - Raab, Marius ED - Rüsseler, Jascha ED - Gross, Tom ED - Schlieder, Christoph ED - Dörner, Dietrich PY - 2012 T2 - Proceedings of KogWis 2012. 11th Biannual Conference of the German Cognitive Science Society SP - 56-56 PB - University of Bamberg Press CY - Bamberg T3 - Schriften aus der Fakultät Wirtschaftsinformatik und Angewandte Informatik der Otto-Friedrich-Universität Bamberg SN - 978-3-86309-101-9 UR - https://fis.uni-bamberg.de/handle/uniba/1254 LA - eng AB - In particular the following areas are covered: introduction and basic concepts; human factors and technological factors; interaction, design, and prototyping; as well as evaluation and usabililty. In evaluation and usability participants will get hands-on experience to empirical methods and eyetracking. ER - TY - CPAPER TI - Modelling Adaptation Effects as Similarity to Dynamic Prototypes AU - Siebers, Michael AU - Folger, Johannes AU - Schineller, Simone AU - Seuß, Dominik AU - Faerber, Stella J. AU - Schmid, Ute ED - Schmid, Ute ED - Siebers, Michael ED - Carbon, Claus-Christian ED - Raab, Marius ED - Rüsseler, Jascha ED - Gross, Tom ED - Schlieder, Christoph ED - Dörner, Dietrich PY - 2012 T2 - Proceedings of KogWis 2012 : 11th Biannual Conference of the German Cognitive Science Society SP - 103-104 PB - University of Bamberg Press CY - Bamberg T3 - Schriften aus der Fakultät Wirtschaftsinformatik und Angewandte Informatik der Otto-Friedrich-Universität Bamberg SN - 978-3-86309-100-2 UR - https://fis.uni-bamberg.de/handle/uniba/1128 LA - eng ER - TY - CPAPER TI - Applying Grammar Inference To Identify Generalized Patterns of Facial Expressions of Pain AU - Schmid, Ute AU - Siebers, Michael AU - Seuß, Dominik AU - Kunz, Miriam AU - Lautenbacher, Stefan PY - 2012 T2 - JMLR: Workshop and Conference Proceedings IS - 21 (2012) = Proceedings of the Eleventh International Conference on Grammatical Inference, ICGI 2012, University of Maryland, College Park, USA, September 5-8, 2012 SP - 183-188 PB - MIT Press CY - Cambridge, Mass. SN - 1938-7228 UR - https://fis.uni-bamberg.de/handle/uniba/1124 LA - eng ER - TY - CPAPER TI - Generalizing Schemas in a Complex Scenario - Can Analogy-Based Training Material Trigger the Acquisition of Solution Principles in Chess? AU - Sonnenberg, Christoph ED - Schmid, Ute ED - Siebers, Michael PY - 2012 T2 - Proceedings of KogWis 2012. 11th Biannual Conference of the German Cognitive Science Society SP - 104-105 PB - University of Bamberg Press CY - Bamberg T3 - Schriften aus der Fakultät Wirtschaftsinformatik und Angewandte Informatik der Otto-Friedrich-Universität Bamberg SN - 978-3-86309-100-2 UR - https://fis.uni-bamberg.de/handle/uniba/1126 LA - eng ER - TY - CPAPER TI - Implicit and explicit learning of artificial grammars from letter strings, visual, and visual-motor patterns AU - Hofmann, Jacqueline AU - Kaiser, Tobias AU - Schmid, Ute ED - Schmid, Ute ED - Siebers, Michael PY - 2012 T2 - Proceedings of KogWis 2012. 11th Biannual Conference of the German Cognitive Science Society SP - 87-88 PB - University of Bamberg Press CY - Bamberg T3 - Schriften aus der Fakultät Wirtschaftsinformatik und Angewandte Informatik der Otto-Friedrich-Universität Bamberg SN - 978-3-86309-100-2 UR - https://fis.uni-bamberg.de/handle/uniba/1102 LA - eng ER - TY - CPAPER TI - MoralLISA – An extension of the analogy model LISA for moral decision making AU - Grossmann, Peter AU - Siebers, Michael AU - Schmid, Ute ED - Barkowsky, Thomas ED - Ragni, Marco ED - Stolzenburg, Frieder PY - 2012 T2 - Human Reasoning and Automated Deduction - KI 2012 Workshop Proceedings SP - 9-16 PB - Universität Bremen CY - Bremen UR - https://fis.uni-bamberg.de/handle/uniba/1106 LA - eng ER - TY - CPAPER TI - A Cognitive Model For Predicting Aesthetical Judgements As Similarity to Dynamic Prototypes AU - Schmid, Ute AU - Siebers, Michael AU - Folger, Johannes AU - Schineller, Simone AU - Seuß, Dominik AU - Raab, Marius AU - Carbon, Claus-Christian AU - Faerber, Stella J. ED - Rußwinkel, Nele ED - Drewitz, Uwe ED - van Rijn, Hedderik PY - 2012 T2 - Proceedings of the 11th international Conference on Cognitive Modeling (ICCM 2012) SP - 13-18 PB - Universitätsbibliothek Technische Universität Berlin CY - Berlin SN - 978-3-7983-2408-4 DO - 10.1016/J.COGSYS.2012.12.002 UR - https://fis.uni-bamberg.de/handle/uniba/1091 LA - eng ER - TY - CPAPER TI - Analogical Problem Solving: Insights from Verbal Reports AU - Gralla, Linn AU - Tenbrink, Thora AU - Siebers, Michael AU - Schmid, Ute ED - Miyake, Naomi ED - Peebles, David ED - Cooper, Richard P. PY - 2012 T2 - Building Bridges Across Cognitive Sciences Around the World : Proceedings of the 34th Annual Meeting of the Cognitive Science Society; Sapporo, Japan, August 1-4, 2012 SP - 396-401 CY - Austin, TX SN - 978-0-9768318-8-4 UR - https://fis.uni-bamberg.de/handle/uniba/1082 LA - eng ER - TY - CPAPER TI - Comparing Automated Pain Classifiers with Human Performance AU - Folger, Johannes AU - Siebers, Michael AU - Kunz, Miriam AU - Lautenbacher, Stefan AU - Schmid, Ute ED - Schmid, Ute ED - Siebers, Michael PY - 2012 T2 - Proceedings of KogWis 2012. 11th Biannual Conference of the German Cognitive Science Society SP - 81 PB - University of Bamberg Press CY - Bamberg T3 - Schriften aus der Fakultät Wirtschaftsinformatik und Angewandte Informatik der Otto-Friedrich-Universität Bamberg SN - 978-3-86309-100-2 UR - https://fis.uni-bamberg.de/handle/uniba/1097 LA - eng ER - TY - CPAPER TI - LISA gets moral - Extension of the analogy system LISA for moral decision making AU - Grossmann, Peter ED - Schmid, Ute ED - Siebers, Michael ED - Carbon, Claus-Christian ED - Raab, Marius ED - Rüsseler, Jascha ED - Gross, Tom ED - Schlieder, Christoph ED - Dörner, Dietrich PY - 2012 T2 - Proceedings of KogWis 2012 : 11th Biannual Conference of the German Cognitive Science Society SP - 86-87 PB - University of Bamberg Press CY - Bamberg T3 - Schriften aus der Fakultät Wirtschaftsinformatik und Angewandte Informatik der Otto-Friedrich-Universität Bamberg SN - 978-3-86309-100-2 UR - https://fis.uni-bamberg.de/handle/uniba/1090 LA - eng ER - TY - CPAPER TI - Semi-Analytic Natural Number Series Induction AU - Siebers, Michael AU - Schmid, Ute ED - Krüger, Antonio ED - Glimm, Birte PY - 2012 T2 - KI 2012: Advances in Artificial Intelligence : 35th Annual German Conference on AI, Saarbrücken, Germany, September 24-27, 2012, Proceedings SP - 249-252 PB - Springer CY - Berlin [u.a.] T3 - Lecture Notes in Computer Science / Lecture Notes in Artificial Intelligence SN - 978-3-642-33346-0 DO - 10.1007/978-3-642-33347-7_25 UR - https://fis.uni-bamberg.de/handle/uniba/1094 LA - eng ER - TY - CPAPER TI - Matchmaking: How similar is what I want to what I get? AU - Munz, Michael AU - Stein, Klaus AU - Sticht, Martin AU - Schmid, Ute PY - 2012 T2 - Working Papers of the 1st International Workshop on Similarity and Analogy-based Methods in AI, SAMAI 2012, August 27, 2012 - Montpellier (France) SP - 13-18 PB - IRIT CY - Toulouse UR - https://fis.uni-bamberg.de/handle/uniba/1018 LA - eng ER - TY - CPAPER TI - Proceedings of KogWis 2012 : 11th Biannual Conference of the German Cognitive Science Society AU - Dörner, Dietrich AU - Goebel, Rainer AU - Oaksford, Mike AU - Pauen, Michael AU - Stern, Elsbeth ED - Schmid, Ute ED - Siebers, Michael ED - Carbon, Claus-Christian ED - Raab, Marius ED - Rüsseler, Jascha ED - Gross, Tom ED - Schlieder, Christoph ED - Dörner, Dietrich PY - 2012 PB - University of Bamberg Press CY - Bamberg T3 - Schriften aus der Fakultät Wirtschaftsinformatik und Angewandte Informatik der Otto-Friedrich-Universität Bamberg SN - 978-3-86309-100-2 DO - 10.20378/irb-445 UR - https://fis.uni-bamberg.de/handle/uniba/445 LA - eng AB - The German cognitive science conference is an interdisciplinary event where researchers from different disciplines -- mainly from artificial intelligence, cognitive psychology, linguistics, neuroscience, philosophy of mind, and anthropology -- and application areas -- such as eduction, clinical psychology, and human-machine interaction -- bring together different theoretical and methodological perspectives to study the mind. The 11th Biannual Conference of the German Cognitive Science Society took place from September 30 to October 3 2012 at Otto-Friedrich-Universität in Bamberg. The proceedings cover all contributions to this conference, that is, five invited talks, seven invited symposia and two symposia, a satellite symposium, a doctoral symposium, three tutorials, 46 abstracts of talks and 23 poster abstracts. KW - - ER - TY - CPAPER TI - From Sensorimotor Graphs to Rules: An Agent Learns from a Stream of Experience AU - Raab, Marius AU - Wernsdorfer, Mark AU - Kitzelmann, Emanuel AU - Schmid, Ute PY - 2011 T2 - Artificial general intelligence : 4th international conference, AGI 2011, Mountain View, CA, USA, August 3 - 6, 2011 ; proceedings SP - 333 - 339 CY - Berlin u.a. T3 - Lecture notes in computer science SN - 978-3-642-22886-5 UR - https://fis.uni-bamberg.de/handle/uniba/5484 LA - eng ER - TY - CHAP TI - Trace-based programming (short entry) AU - Schmid, Ute AU - Flener, Pierre PY - 2011 T2 - Encyclopedia of Machine Learning SP - 989 CY - New York SN - 9780387345581 UR - https://fis.uni-bamberg.de/handle/uniba/5480 LA - eng ER - TY - GEN TI - Cognitive Systems Research AU - Schmid, Ute PY - 2011 PB - Elsevier Science CY - Amsterdam u.a. UR - https://fis.uni-bamberg.de/handle/uniba/5440 LA - other ER - TY - CPAPER TI - Exploring the needs of people with dementia regarding assistive technology to save quality of life and independent living at home AU - Streffing, Gaby AU - Siebers, Michael AU - Gräßel, Elmar AU - Schmid, Ute PY - 2011 T2 - Proceedings of the EPA 2011 ; 19th European Congress of Psychiatry Wien 12-15 March, 2011 CY - Wien UR - https://fis.uni-bamberg.de/handle/uniba/5444 LA - eng ER - TY - CHAP TI - Inductive Programming AU - Flener, Pierre AU - Schmid, Ute PY - 2011 T2 - Encyclopedia of Machine Learning SP - 537 - 544 CY - New York SN - 9780387345581 UR - https://fis.uni-bamberg.de/handle/uniba/5438 LA - eng ER - TY - JOUR TI - Inductive Rule Learning on the Knowledge Level AU - Schmid, Ute AU - Kitzelmann, Emanuel PY - 2011 JO - Cognitive systems research VL - 12 IS - 3-4: Special Issue on Complex Cognition SP - 237 - 248 SN - 1389-0417 DO - 10.1016/j.cogsys.2010.12.002 UR - https://fis.uni-bamberg.de/handle/uniba/5442 LA - eng ER - TY - JOUR TI - The Challenge of Complex Cognition AU - Schmid, Ute AU - Ragni, Marco AU - Gonzalez, Cleotilde AU - Funke, Joachim PY - 2011 JO - Cognitive systems research VL - 12 IS - 3-4: Special Issue on Complex Cognition SP - 211 - 218 SN - 1389-0417 UR - https://fis.uni-bamberg.de/handle/uniba/5433 LA - eng ER - TY - CPAPER TI - How Visible are Different Variations of Spatial Features and Relations in Logos and How Does Visibility Affect Prototype Generation? AU - Schmid, Ute AU - Grossmann, Peter AU - Wachter, Markus AU - Raab, Marius AU - Carbon, Claus-Christian AU - Faerber, Stella J. PY - 2011 T2 - Visibility in Information Spaces and in Geographic Environments. Post- Proceedings of the KI'11 Workshop (October 4th, 2011, TU Berlin, Germany) SP - ,23 - 34 CY - Bamberg UR - https://fis.uni-bamberg.de/handle/uniba/5415 LA - eng ER - TY - CHAP TI - Programming by Demonstration (short entry) AU - Flener, Pierre AU - Schmid, Ute PY - 2011 T2 - Encyclopedia of Machine Learning SP - 805 CY - New York SN - 9780387345581 UR - https://fis.uni-bamberg.de/handle/uniba/5429 LA - eng ER - TY - JOUR TI - Tut das weh? : automatisierte Schmerzidentifikation anhand der Mimik AU - Schmid, Ute AU - Siebers, Michael AU - Kunz, Miriam AU - Lautenbacher, Stefan PY - 2011 JO - uni.vers : Forschung IS - 17: Digital Humanities : Technologien für die Geisteswissenschaften SP - 32 - 35 SN - 2195-2558 UR - https://fis.uni-bamberg.de/handle/uniba/5377 LA - deu ER - TY - JOUR TI - Schön ist, was man kennt : Modellierung von Gewöhnungseffekten bei ästhetischen Urteilen AU - Schmid, Ute AU - Faerber, Stella J. AU - Raab, Marius Hans AU - Ivens, Björn Sven AU - Carbon, Claus-Christian PY - 2011 JO - uni.vers : Forschung IS - 17: Digital Humanities : Technologien für die Geisteswissenschaften SP - 40-43 SN - 2195-2558 UR - https://fis.uni-bamberg.de/handle/uniba/5337 LA - deu ER - TY - CHAP TI - Modellierung psychischer Prozesse AU - Dörner, Dietrich AU - Schmid, Ute PY - 2011 T2 - Psychologie : eine Einführung in ihre Grundlagen und Anwendungsfelder SP - 331 - 345 CY - Stuttgart ET - 4., vollst. überarb. und erw. Aufl. SN - 9783170214569 UR - https://fis.uni-bamberg.de/handle/uniba/4484 LA - deu ER - TY - CPAPER TI - Visibility in Information Spaces and in Geographic Environments : Post-Proceedings of the KI'11 Workshop (October 4th, 2011, TU Berlin, Germany) AU - Henrich, Andreas AU - Schlieder, Christoph AU - Schmid, Ute AU - Seifert, Inessa AU - Saendig, Bertram AU - Kremer, Dominik AU - Grossmann, Peter AU - Wachter, Markus AU - Raab, Marius AU - Carbon, Claus-Christian AU - Faerber, Stella J. ED - Henrich, Andreas ED - Schlieder, Christoph ED - Schmid, Ute PY - 2011 PB - opus CY - Bamberg T3 - Bamberger Beiträge zur Wirtschaftsinformatik und Angewandten Informatik UR - https://fis.uni-bamberg.de/handle/uniba/321 LA - eng AB - In the post-proceedings of the Workshop "Visibility in Information Spaces and in Geographic Environments" a selection of research papers is presented where the topic of visibility is addressed in different contexts. Visibility governs information selection in geographic environments as well as in information spaces and in cognition. The users of social media navigate in information spaces and at the same time, as embodied agents, they move in geographic environments. Both activities follow a similar type of information economy in which decisions by individuals or groups require a highly selective filtering to avoid information overload. In this context, visibility refers to the fact that in social processes some actors, topics or places are more salient than others. Formal notions of visibility include the centrality measures from social network analysis or the plethora of web page ranking methods. Recently, comparable approaches have been proposed to analyse activities in geographic environments: Place Rank, for instance, describes the social visibility of urban places based on the temporal sequence of tourist visit patterns. The workshop aimed to bring together researchers from AI, Geographic Information Science, Cognitive Science, and other disciplines who are interested in understanding how the different forms of visibility in information spaces and geographic environments relate to one another and how the results from basic research can be used to improve spatial search engines, geo-recommender systems or location-based social networks. KW - Raum-zeitliches Verhalten, Mobile Assistenz, Visualisierung , Prototypen, Geo-Information Retrieval KW - Raum-zeitliches Verhalten KW - Mobile Assistenz KW - Visualisierung KW - Prototypen KW - Geo-Information Retrieval ER - TY - CPAPER TI - Data-Driven Detection of Recursive Program Schemes AU - Hofmann, Martin AU - Schmid, Ute PY - 2010 T2 - Proceedings of the 19th European Conference on Artificial Intelligence ; Lissabon 16. - 20. August 2010 SP - 1063 - 1064 CY - Amsterdam T3 - Frontiers in Artificial Intelligence and Applications UR - https://fis.uni-bamberg.de/handle/uniba/3997 LA - eng ER - TY - CPAPER TI - Learning in Analogical Reasoning: Greedy and Ubiquitous or Context- Dependent AU - Lewandowski, Jirka AU - Schmid, Ute PY - 2010 T2 - Proceedings of KogWis 2010 : 10th Biannual Meeting of the German Society for Cognitive Science ; Potsdam, Oct. 3 - 6, 2010 SP - 138 CY - Potsdam UR - https://fis.uni-bamberg.de/handle/uniba/3993 LA - eng ER - TY - CPAPER TI - Tracking von Gesichtsmimik mit Hilfe von Gitterstrukturen zur Klassifikation von schmerzrelevanten Action Units AU - Barthold, Christine AU - Papst, Anton AU - Küblbeck, Christian AU - Wittenberg, Thomas AU - Lautenbacher, Stefan AU - Schmid, Ute AU - Sven, Friedl PY - 2010 T2 - Bildverarbeitung für die Medizin 2010 : Algorithmen - Systeme - Anwendungen ; Proceedings des BVM-Workshops vom 14. bis 16. März 2010 in Aachen SP - 455 - 460 CY - Berlin u.a. UR - https://fis.uni-bamberg.de/handle/uniba/4001 LA - deu ER - TY - CPAPER TI - Analytical Functional Inductive Programming as Cognitive Rule Acquisition Device AU - Schmid, Ute PY - 2010 T2 - Dagstuhl Seminar Proceedings 10302 "Learning paradigms in dynamic environments" SP - 9 UR - https://fis.uni-bamberg.de/handle/uniba/3958 LA - eng ER - TY - CPAPER TI - Incident Mining using Structural Prototypes AU - Schmid, Ute AU - Hofmann, Martin AU - Bader, Florian AU - Häberle, Tilmann AU - Schneider, Thomas PY - 2010 T2 - Trends in applied intelligent systems : 23rd International Conference on Industrial Engineering and Other Applications of Applied Intelligent Systems, IEA AIE 2010, Cordoba, Spain, June 1 - 4, 2010 ; proceedings SP - 327 - 336 CY - Berlin u.a. UR - https://fis.uni-bamberg.de/handle/uniba/3957 LA - eng ER - TY - CPAPER TI - Interleaving forward backward feature selection AU - Siebers, Michael AU - Schmid, Ute PY - 2010 T2 - Proceedings of the International Conference on Knowledge Discovery and Information Retrieval : Valencia, Spain, October 25 - 28, 2010 ; one of three integrated conferences that constitute the International Joint Conference on Knowledge Discovery, Knowledge Engineering and Knowledge Management (IC3K) SP - 454 - 457 PB - SciTePress CY - Setúbal UR - https://fis.uni-bamberg.de/handle/uniba/3952 LA - eng ER - TY - CPAPER TI - Invited Symposium Complex Cognition (Speakers: Kai-Uwe Kühnberger, Claus Möbus, Pat Langley, Dietrich Dörner) AU - Schmid, Ute AU - Barkowski, T. PY - 2010 T2 - Proceedings of KogWis 2010 : 10th Biannual Meeting of the German Society for Cognitive Science ; Potsdam, Oct. 3 - 6, 2010 SP - 21 - 24 UR - https://fis.uni-bamberg.de/handle/uniba/3950 LA - eng ER - TY - CPAPER TI - Approaches and Applications of Inductive Programming : third International Workshop, AAIP 2009, Edinburgh, UK, September 4, 2009 ; revised Papers ED - Kitzelmann, Emanuel ED - Schmid, Ute ED - Plasmeijer, Rinus PY - 2010 PB - Springer CY - Berlin u.a. T3 - Lecture Notes in Computer Science SN - 978-3-642-11930-9 DO - 10.1007/978-3-642-11931-6 UR - https://fis.uni-bamberg.de/handle/uniba/3378 LA - eng ER - TY - CPAPER TI - Porting IGORII from MAUDE to HASKELL AU - Hofmann, Martin AU - Kitzelmann, Emanuel AU - Schmid, Ute PY - 2010 T2 - Approaches and Applications of Inductive Programming : third International Workshop, AAIP 2009, Edinburgh, UK, September 4, 2009 ; revised Papers SP - 140 - 158 CY - Berlin u.a. T3 - Lecture Notes in Computer Science SN - 978-3-642-11930-9 DO - 10.1007/978-3-642-11931-6 UR - https://fis.uni-bamberg.de/handle/uniba/3385 LA - eng ER - TY - CPAPER TI - Classifying Facial Pain Expressions - Individual Classifiers vs. Global Classifiers AU - Siebers, Michael AU - Kunz, Miriam AU - Lautenbacher, Stefan AU - Schmid, Ute PY - 2009 T2 - Proceedings of the 4th Workshop Emotion and Computing - Current Research and Future Impact ; Paderborn, Germany, September 15th, 2009 ; Scientific Research Papers SP - 18 - 25 CY - Stuttgart UR - https://fis.uni-bamberg.de/handle/uniba/20109 LA - eng ER - TY - BOOK TI - Proceedings of the ACM SIGPLAN Workshop on Approaches and Applications of Inductive Programming (AAIP 2009) AU - Schmid, Ute AU - Kitzelmann, Emanuel AU - Plasmeijer, Rinus PY - 2009 PB - Otto-Friedrich-Univ. Bamberg, Fakultät Wirtschaftsinformatik und Angewandte Informatik CY - Bamberg T3 - Bamberger Beiträge zur Wirtschaftsinformatik und Angewandten Informatik UR - https://fis.uni-bamberg.de/handle/uniba/19763 LA - eng AB - Inductive programming is concerned with the automated construction of declarative, often functional, recursive programs from incomplete specifications such as input/output examples. The inferred program must be correct with respect to the provided examples in a generalising sense: it should be neither equivalent to them, nor inconsistent. Inductive programming algorithms are guided explicitly or implicitly by a language bias (the class of programs that can be induced) and a search bias (determining which generalised program is constructed first). Induction strategies are either generate-and-test or example-driven. In generate-and-test approaches, hypotheses about candidate programs are generated independently from the given specifications. Program candidates are tested against the given specification and one or more of the best evaluated candidates are developed further. In analytical approaches, candidate programs are constructed in an example-driven way. While generate-and-test approaches can -- in principle -- construct any kind of program, analytical approaches have a more limited scope. On the other hand, efficiency of induction is much higher in analytical approaches. Inductive programming is still mainly a topic of basic research, exploring how the intellectual ability of humans to infer generalised recursive procedures from incomplete evidence can be captured in the form of synthesis methods. Intended applications are mainly in the domain of programming assistance -- either to relieve professional programmers from routine tasks or to enable non-programmers to some limited form of end-user programming. Furthermore, in the future, inductive programming techniques might be applied to further areas such as supporting the inference of lemmata in theorem proving or learning grammar rules. Inductive automated program construction has been originally addressed by researchers in artificial intelligence and machine learning. During the last years, some work on exploiting induction techniques has been started also in the functional programming community. Therefore, the third workshop on |Approaches and Applications of Inductive Programming| took place for the first time in conjunction with the ACM SIGPLAN International Conference on Functional Programming (ICFP 2009). The first and second workshop were associated with the International Conference on Machine Learning (ICML 2005) and the European Conference on Machine Learning (ECML 2007). AAIP´09 aimed to bring together researchers from the functional programming and the artificial intelligence communities, working in the field of inductive functional programming, and advance fruitful interactions between these communities with respect to programming techniques for inductive programming algorithms, the identification of challenge problems and potential applications. For everybody interested in inductive programming we recommend to visit the website: www.inductive-programming.org. KW - Induktive Programmierung , Funktionale Programmierung , Evolutionäre Programmierung , Programmsynthese KW - Inductive Programming , Functional Programming , Evolutionary Programming , Program synthesis KW - Induktive Programmierung KW - Funktionale Programmierung KW - Evolutionäre Programmierung KW - Programmsynthese KW - Inductive Programming KW - Functional Programming KW - Evolutionary Programming KW - Program synthesis ER - TY - BOOK TI - Proceedings of the KI 2009 Workshop on Complex Cognition AU - Schmid, Ute AU - Ragni, Marco AU - Knauff, Markus PY - 2009 PB - Otto-Friedrich-Univ. Bamberg, Fakultät Wirtschaftsinformatik und Angewandte Informatik CY - Bamberg T3 - Bamberger Beiträge zur Wirtschaftsinformatik und Angewandten Informatik UR - https://fis.uni-bamberg.de/handle/uniba/19766 LA - eng AB - The KI ´09 workshop on Complex Cognition was a joint venture of the Cognition group of the Special Interest Group Artificial Intelligence of the German Computer Science Society (Gesellschaft für Informatik) and the German Cognitive Science Association. Dealing with complexity has become one of the great challenges for modern information societies. To reason and decide, plan and act in complex domains is no longer limited to highly specialized professionals in restricted areas such as medical diagnosis, controlling technical processes, or serious game playing. Complexity has reached everyday life and affects people in such mundane activities as buying a train ticket, investing money, or connecting a home desktop to the internet. Research in cognitive AI can contribute to supporting people navigating through the jungle of everyday reasoning, decision making, planning and acting by providing intelligent support technology. Lessons learned from expert systems research of the nineteen-eighties show that the aim should not be to provide for fully automated systems which can solve specialized tasks autonomously but instead to develop interactive assistant systems where user and system work together by taking advantage of the respective strengths of human and machine. To accomplish a smooth collaboration between humans and intelligent systems, basic research in cognition is a necessary precondition. Insights into cognitive structures and processes underlying successful human reasoning and planning can provide suggestions for algorithm design. Even more important, insights into restrictions and typical errors and misconceptions of the cognitive systems provide information about those parts of a complex task from which the human should be relieved. For successful human-computer interaction in complex domains it has, furthermore, to be decided which information should be presented when, in what way, to the user. We strongly believe that symbolic approaches of AI and psychological research of higher cognition are at the core of success for the endeavor to create intelligent assistant system for complex domains. While insight into the neurological processes of the brain and into the realization of basic processes of perception, attention and senso-motoric coordination are important for the basic understanding of the principles of human intelligence, these processes have a much too fine granularity for the design and realization of interactive systems which must communicate with the user on knowledge level. If human system users are not to be incapacitated by a system, system decisions must be transparent for the user and the system must be able to provide explanations for the reasons of its proposals and recommendations. Therefore, even when some of the underlying algorithms are based on statistical or neuronal approaches, the top-level of such systems must be symbolical and rule-based. The papers presented at this workshop on complex cognition give an inspiring and promising overview of current work in the field which can provide first building stones for our endeavor to create knowledge level intelligent assistant systems for complex domains. The topics cover modelling basic cognitive processes, interfacing subsymbolic and symbolic representations, dealing with continuous time, Bayesian identification of problem solving strategies, linguistically inspired methods for assessing complex cognitive processes and complex domains such as recognition of sketches, predicting changes in stocks, spatial information processing, and coping with critical situations. KW - Kognition, Kognitive Modellierung, Kognitionspsychologie, Künstliche Intelligenz KW - Cognition, Cognitive Modelling, Cognitive Psychology, Artificial Intelligence KW - Kognition KW - Kognitive Modellierung KW - Kognitionspsychologie KW - Künstliche Intelligenz KW - Cognition KW - Cognitive Modelling KW - Cognitive Psychology KW - Artificial Intelligence ER - TY - JOUR TI - Das Internet als Informationsquelle für pflegende Angehörige eines Demenzpatienten AU - Gräßel, Elmar AU - Bleich, Stefan AU - Meyer-Wegener, Klaus AU - Schmid, Ute AU - Kornhuber, Johannes AU - Prokosch, Hans-Ulrich PY - 2009 JO - Psychiatrische Praxis VL - 36 IS - 3 SP - 115-118 SN - 0303-4259 DO - 10.1055/s-2008-1067550 UR - https://fis.uni-bamberg.de/handle/uniba/18220 LA - deu ER - TY - CPAPER TI - Girls And Computer Science -- Attitude Formation Via Practical Experience AU - Grabisch, Sanne AU - Stein, Klaus AU - Schmid, Ute PY - 2009 T2 - 2009 Gender & ICT : Online Proceedings of the 5th European Symposium on Gender & ICT, Digital Cultures: Participation - Empowerment - Diversity, March 5 - 7, 2009 - University of Bremen CY - Bremen, UR - https://fis.uni-bamberg.de/handle/uniba/18217 LA - eng ER - TY - CPAPER TI - Proceedings of the KI 2009 Workshop on Complex Cognition ED - Knauff, Markus ED - Ragni, Marco ED - Schmid, Ute PY - 2009 PB - opus CY - Bamberg T3 - Bamberger Beiträge zur Wirtschaftsinformatik und Angewandten Informatik UR - https://fis.uni-bamberg.de/handle/uniba/178 LA - eng AB - The KI ´09 workshop on Complex Cognition was a joint venture of the Cognition group of the Special Interest Group Artificial Intelligence of the German Computer Science Society (Gesellschaft für Informatik) and the German Cognitive Science Association. Dealing with complexity has become one of the great challenges for modern information societies. To reason and decide, plan and act in complex domains is no longer limited to highly specialized professionals in restricted areas such as medical diagnosis, controlling technical processes, or serious game playing. Complexity has reached everyday life and affects people in such mundane activities as buying a train ticket, investing money, or connecting a home desktop to the internet. Research in cognitive AI can contribute to supporting people navigating through the jungle of everyday reasoning, decision making, planning and acting by providing intelligent support technology. Lessons learned from expert systems research of the nineteen-eighties show that the aim should not be to provide for fully automated systems which can solve specialized tasks autonomously but instead to develop interactive assistant systems where user and system work together by taking advantage of the respective strengths of human and machine. To accomplish a smooth collaboration between humans and intelligent systems, basic research in cognition is a necessary precondition. Insights into cognitive structures and processes underlying successful human reasoning and planning can provide suggestions for algorithm design. Even more important, insights into restrictions and typical errors and misconceptions of the cognitive systems provide information about those parts of a complex task from which the human should be relieved. For successful human-computer interaction in complex domains it has, furthermore, to be decided which information should be presented when, in what way, to the user. We strongly believe that symbolic approaches of AI and psychological research of higher cognition are at the core of success for the endeavor to create intelligent assistant system for complex domains. While insight into the neurological processes of the brain and into the realization of basic processes of perception, attention and senso-motoric coordination are important for the basic understanding of the principles of human intelligence, these processes have a much too fine granularity for the design and realization of interactive systems which must communicate with the user on knowledge level. If human system users are not to be incapacitated by a system, system decisions must be transparent for the user and the system must be able to provide explanations for the reasons of its proposals and recommendations. Therefore, even when some of the underlying algorithms are based on statistical or neuronal approaches, the top-level of such systems must be symbolical and rule-based. The papers presented at this workshop on complex cognition give an inspiring and promising overview of current work in the field which can provide first building stones for our endeavor to create knowledge level intelligent assistant systems for complex domains. The topics cover modelling basic cognitive processes, interfacing subsymbolic and symbolic representations, dealing with continuous time, Bayesian identification of problem solving strategies, linguistically inspired methods for assessing complex cognitive processes and complex domains such as recognition of sketches, predicting changes in stocks, spatial information processing, and coping with critical situations. KW - Kognition, Kognitive Modellierung, Kognitionspsychologie, Künstliche Intelligenz KW - Cognition, Cognitive Modelling, Cognitive Psychology, Artificial Intelligence KW - Kognition KW - Kognitive Modellierung KW - Kognitionspsychologie KW - Künstliche Intelligenz KW - Cognition KW - Cognitive Modelling KW - Cognitive Psychology KW - Artificial Intelligence ER - TY - CPAPER TI - Proceedings of the ACM SIGPLAN Workshop on Approaches and Applications of Inductive Programming (AAIP 2009) ED - Kitzelmann, Emanuel ED - Schmid, Ute ED - Plasmeijer, Rinus PY - 2009 PB - opus CY - Bamberg T3 - Bamberger Beiträge zur Wirtschaftsinformatik und Angewandten Informatik UR - https://fis.uni-bamberg.de/handle/uniba/175 LA - eng AB - Inductive programming is concerned with the automated construction of declarative, often functional, recursive programs from incomplete specifications such as input/output examples. The inferred program must be correct with respect to the provided examples in a generalising sense: it should be neither equivalent to them, nor inconsistent. Inductive programming algorithms are guided explicitly or implicitly by a language bias (the class of programs that can be induced) and a search bias (determining which generalised program is constructed first). Induction strategies are either generate-and-test or example-driven. In generate-and-test approaches, hypotheses about candidate programs are generated independently from the given specifications. Program candidates are tested against the given specification and one or more of the best evaluated candidates are developed further. In analytical approaches, candidate programs are constructed in an example-driven way. While generate-and-test approaches can -- in principle -- construct any kind of program, analytical approaches have a more limited scope. On the other hand, efficiency of induction is much higher in analytical approaches. Inductive programming is still mainly a topic of basic research, exploring how the intellectual ability of humans to infer generalised recursive procedures from incomplete evidence can be captured in the form of synthesis methods. Intended applications are mainly in the domain of programming assistance -- either to relieve professional programmers from routine tasks or to enable non-programmers to some limited form of end-user programming. Furthermore, in the future, inductive programming techniques might be applied to further areas such as supporting the inference of lemmata in theorem proving or learning grammar rules. Inductive automated program construction has been originally addressed by researchers in artificial intelligence and machine learning. During the last years, some work on exploiting induction techniques has been started also in the functional programming community. Therefore, the third workshop on |Approaches and Applications of Inductive Programming| took place for the first time in conjunction with the ACM SIGPLAN International Conference on Functional Programming (ICFP 2009). The first and second workshop were associated with the International Conference on Machine Learning (ICML 2005) and the European Conference on Machine Learning (ECML 2007). AAIP´09 aimed to bring together researchers from the functional programming and the artificial intelligence communities, working in the field of inductive functional programming, and advance fruitful interactions between these communities with respect to programming techniques for inductive programming algorithms, the identification of challenge problems and potential applications. For everybody interested in inductive programming we recommend to visit the website: www.inductive-programming.org. KW - Induktive Programmierung , Funktionale Programmierung , Evolutionäre Programmierung , Programmsynthese KW - Inductive Programming , Functional Programming , Evolutionary Programming , Program synthesis KW - Induktive Programmierung KW - Funktionale Programmierung KW - Evolutionäre Programmierung KW - Programmsynthese KW - Inductive Programming KW - Functional Programming KW - Evolutionary Programming KW - Program synthesis ER - TY - CPAPER TI - Mapping and inference in analogical problem solving - As much as needed or as much as possible? AU - Wiese, Eva AU - Konerding, Uwe AU - Schmid, Ute PY - 2008 T2 - Proceedings of the 30th Annual ... SP - 927 - 932 CY - Mahwah, NJ UR - https://fis.uni-bamberg.de/handle/uniba/20130 LA - deu ER - TY - JOUR TI - Cognition and AI AU - Schmid, Ute PY - 2008 JO - Künstliche Intelligenz : KI IS - 1 = Schwerpunkt: KI und Kognition SP - 5 - 7 UR - https://fis.uni-bamberg.de/handle/uniba/18252 LA - eng ER - TY - CPAPER TI - An optimization framework for classifier learning from image data for computer-assisted diagnosis AU - Mennicke, Jörg AU - Münzenmayer, Christian AU - Wittenberg, Thomas AU - Schmid, Ute PY - 2008 T2 - 4th European Conference of the International Federation for Medical and Biological Engineering ; eMBEC 2008 ; Engineering for Health ; 23-27 November, FC&CC, Antwerp, Belgium SP - 629 - 632 CY - Heidelberg UR - https://fis.uni-bamberg.de/handle/uniba/18214 LA - eng ER - TY - CPAPER TI - Analysis and Evaluation of Inductive Programming Systems in a Higher- Order Framework AU - Hofmann, Martin AU - Kitzelmann, Emanuel AU - Schmid, Ute PY - 2008 T2 - KI 2008: Advances in artificial intelligence : 31th Annual German Conference on AI, KI 2008, Kaiserslautern, Germany, September 23 - 26, 2008 ; proceedings SP - 78 - 86 CY - Berlin u.a. T3 - Lecture notes in computer science DO - 10.1007/978-3-540-85845-4 UR - https://fis.uni-bamberg.de/handle/uniba/18215 LA - deu ER - TY - JOUR TI - Gasteditorial: KI und Kognition AU - Schmid, Ute PY - 2008 JO - Künstliche Intelligenz : KI IS - 1 = Schwerpunkt: KI und Kognition SP - 4 SN - 0933-1875 UR - https://fis.uni-bamberg.de/handle/uniba/18211 LA - deu ER - TY - GEN TI - Künstliche Intelligenz : KI ; Forschung, Entwicklung, Erfahrungen ; Organ des Fachbereichs 1 Künstliche Intelligenz der Gesellschaft für Informatik e.V., GI AU - Schmid, Ute PY - 2008 PB - Böttcher IT-Verl. CY - Bremen UR - https://fis.uni-bamberg.de/handle/uniba/18210 LA - deu ER - TY - CPAPER TI - Spanning the Middle Ground between Classical and Temporal Planning AU - Wullinger, Peter AU - Schmid, Ute AU - Scholz, Ulrich PY - 2008 T2 - Proceedings of the 22nd Workshop on Planen, Scheduling und Konfigurieren, Entwerfen (PuK 2008) CY - Oldenburg UR - https://fis.uni-bamberg.de/handle/uniba/17827 LA - eng ER - TY - BOOK TI - Classifier learning for imbalanced data : a comparison of kNN, SVM, and decision tree learning AU - Mennicke, Jörg AU - Münzenmayer, Christian AU - Schmid, Ute PY - 2008 PB - VDM Verlag Dr. Müller CY - Saarbrücken SN - 978-3-8364-9223-2 UR - https://fis.uni-bamberg.de/handle/uniba/17004 LA - eng ER - TY - CHAP TI - V. Denken und Problemlösen ; 14. Computermodelle des Problemlösens AU - Schmid, Ute PY - 2008 T2 - Allgemeine Psychologie SP - 601-628 CY - Heidelberg ET - 2., neubearb. Aufl. SN - 978-3-8274-1780-0 UR - https://fis.uni-bamberg.de/handle/uniba/16749 LA - deu ER - TY - CPAPER TI - Inductive Synthesis of Recursive Functional Programs - A Comparison of Three Systems AU - Hofmann, Martin AU - Hirschberger, Andreas AU - Kitzelmann, Emanuel AU - Schmid, Ute PY - 2007 T2 - KI 2007: advances in artificial intelligence : 30th Annual German Conference on AI, KI 2007, Osnabrück, Germany, September 10-13, 2007 ; proceedings SP - 468 - 472 SN - 978-3-540-74564-8 UR - https://fis.uni-bamberg.de/handle/uniba/16792 LA - eng ER - TY - CPAPER TI - ECML 2007 PKDD Warsaw, Poland ; The 18th European Conference on Machine Learning and the 11th European Conference on Principles and Practice of Knowledge Discovery in Databases ; Proceedings of the Workshop on Approaches and Applications of Inductive Programming ; AAIP'07, September 17, 2007, Warsaw, Poland ED - Kitzelmann, Emanuel ED - Schmid, Ute PY - 2007 PB - Faculty of Information Systems and Applied Computer Sciences, University of Bamberg CY - Bamberg UR - https://fis.uni-bamberg.de/handle/uniba/16742 LA - deu ER - TY - JOUR TI - Transformational and derivational strategies in analogical problem solving AU - Schelhorn, Sven-Eric AU - Griego, Jacqueline AU - Schmid, Ute PY - 2007 JO - Cognitive processing : international quarterly of cognitive science VL - 8 IS - 1 SP - 45 - 55 SN - 1612-4790 UR - https://fis.uni-bamberg.de/handle/uniba/16747 LA - eng ER - TY - CPAPER TI - Analogy by abstraction AU - Weller, Stephan AU - Schmid, Ute PY - 2006 T2 - Proceedings of the seventh International conference on cognitive modeling ; (ICCM 2006) ; Trieste, Italy, 5-8 April 2006 CY - Trieste UR - https://fis.uni-bamberg.de/handle/uniba/14661 LA - eng ER - TY - JOUR TI - Inductive Synthesis of Functional Programs - an Explanation Based Generalization Approach AU - Kitzelmann, Emanuel AU - Schmid, Ute PY - 2006 JO - Journal of machine learning research : JMLR VL - 7 IS - Feb. = Special Topic on Approaches and Applications of Inductive Programming SP - 429 - 454 SN - 1532-4435 UR - https://fis.uni-bamberg.de/handle/uniba/14666 LA - eng ER - TY - CHAP TI - Computermodelle des Denkens und Problemlösens AU - Schmid, Ute PY - 2006 T2 - Denken und Problemlösen SP - 483 - 547 CY - Göttingen u.a. SN - 978-3-8017-0527-5 UR - https://fis.uni-bamberg.de/handle/uniba/13925 LA - deu ER - TY - JOUR TI - Metaphors and heuristic-driven theory projection (HDTP) AU - Schmid, Ute AU - Gust, Helmar AU - Kühnberger, Kai-Uwe PY - 2006 JO - Theoretical computer science : the journal of the EATCS VL - 354 IS - 1 SP - 98-117 SN - 0304-3975 UR - https://fis.uni-bamberg.de/handle/uniba/13189 LA - eng ER - TY - CHAP TI - A Cognitive Model of Learning by Doing AU - Schmid, Ute PY - 2005 T2 - Models and human reasoning : Bernd Mahr zum 60. Geburtstag SP - 235 - 252 CY - Berlin ET - 1. Aufl. SN - 3896855395 UR - https://fis.uni-bamberg.de/handle/uniba/13150 LA - eng ER - TY - CPAPER TI - An Explanation Based Generalization Approach to Inductive Synthesis of Functional Programs AU - Kitzelmann, Emanuel AU - Schmid, Ute PY - 2005 T2 - Workshop on Approaches and Applications of Inductive Programming (AAIP), to be held on August 7th 2005 in conjunction with the 22nd International Conference on Machine Learning (ICML 2005) in Bonn, Germany : Proceedings UR - https://fis.uni-bamberg.de/handle/uniba/13153 LA - eng ER - TY - CPAPER TI - Ontologies as a Cue for the Metaphorical Meaning of Technical Concepts AU - Gust, Helmar AU - Kühnberger, Kai-Uwe AU - Schmid, Ute PY - 2004 T2 - ILCC 2004, International Language and Cognition Conference ; 10-12 September 2004 : Abstracts UR - https://fis.uni-bamberg.de/handle/uniba/13193 LA - eng ER - TY - CPAPER TI - Ontological Aspects of Computing Analogies AU - Schmid, Ute PY - 2004 T2 - Proceedings of the Sixth International Conference on Cognitive Modeling : 6th ICCM 2004, integrating models: July 30- August 1, Carnegie Mellon University SP - 350 - 351 CY - London u.a. UR - https://fis.uni-bamberg.de/handle/uniba/13148 LA - eng ER - TY - RPRT TI - Computermodelle des Denkens und Problemlösens AU - Schmid, Ute PY - 2004 CY - Bamberg UR - https://fis.uni-bamberg.de/handle/uniba/11595 LA - deu ER - TY - CPAPER TI - Automatic synthesis of XSL-transformations from example documents AU - Schmid, Ute AU - Waltermann, J. PY - 2004 T2 - Proceedings of the IASTED International Conference on Artificial Intelligence and Applications ; as part of the 22nd IASTED International Multi-Conference on Applied Informatics ; February 16 - 18, 2004, Innsbruck, Austria ; (AIA 2004) SP - 252 - 257 CY - Anaheim u.a. UR - https://fis.uni-bamberg.de/handle/uniba/11577 LA - eng ER - TY - CPAPER TI - Anti-unification as an approach to analogical reasoning and generalization. (Poster Abstract) AU - Schmid, Ute AU - Burghardt, J. AU - Wagner, U. PY - 2003 T2 - The logic of cognitive systems : proceedings of the Fifth International Conference on Cognitive Modeling ; ICCM-5 2003 SP - 293 - 294 CY - Bamberg UR - https://fis.uni-bamberg.de/handle/uniba/11633 LA - eng ER - TY - RPRT TI - Anti-unification of axiomatic systems AU - Gust, Helmar AU - Schmid, Ute AU - Kühnberger, Kai-Uwe PY - 2003 CY - Osnabrück T3 - Work in progress report UR - https://fis.uni-bamberg.de/handle/uniba/11621 LA - eng ER - TY - JOUR TI - Inductive synthesis of functional programs - Learning domain-specific control rules and abstract schemes AU - Schmid, Ute PY - 2003 JO - Künstliche Intelligenz : KI ; Forschung, Entwicklung, Erfahrungen ; Organ des Fachbereichs 1 Künstliche Intelligenz der Gesellschaft für Informatik e.V. VL - 17 IS - 3 SP - 75 - 77 SN - 0933-1875 UR - https://fis.uni-bamberg.de/handle/uniba/11629 LA - eng ER - TY - CPAPER TI - Metaphors and anti-unification AU - Gust, H. AU - Kühnberger, K.-U. AU - Schmid, Ute PY - 2003 T2 - Algebraic methods in language processing : - AMiLP-3 ( AMiLP-3 Verona, Italy 25-27 August 2003) SP - 111 - 123 CY - Twente UR - https://fis.uni-bamberg.de/handle/uniba/11625 LA - eng ER - TY - JOUR TI - A closer look at structural similarity in analogical transfer AU - Schmid, Ute AU - Wirth, J. AU - Polkehn, K. PY - 2003 JO - Cognitive science quarterly : CSQ ; an international journal of basic and applied research VL - 3 IS - 1 SP - 57 - 89 SN - 1612-4790 UR - https://fis.uni-bamberg.de/handle/uniba/11599 LA - eng ER - TY - BOOK TI - Inductive synthesis of functional programs : universal planning, folding of finite programs, and schema abstraction by analogical reasoning AU - Schmid, Ute PY - 2003 PB - Springer CY - Berlin u.a. T3 - Lecture notes in computer science SN - 978-3-540-40174-2 DO - 10.1007/b12055 UR - https://fis.uni-bamberg.de/handle/uniba/11597 LA - eng ER - TY - CPAPER TI - Integrating planning, learning, and analogy - A prototype system. ( Poster Abstract) AU - Beckmann, M. AU - Lörken, C. AU - Schmid, Ute PY - 2003 T2 - The logic of cognitive systems : proceedings of the Fifth International Conference on Cognitive Modeling ; ICCM-5 2003 SP - 235 - 236 CY - Bamberg UR - https://fis.uni-bamberg.de/handle/uniba/11603 LA - eng ER - TY - CPAPER TI - Solving predictive analogy tasks with anti-unification AU - Gust, H. AU - Kühnberger, K.-U. AU - Schmid, Ute PY - 2003 T2 - Joint International Conference on Cognitive Science (ICCS/ASCS-2003), Sydney, Australia 13 - 17 July 2003 CY - Sydney, Australia UR - https://fis.uni-bamberg.de/handle/uniba/11594 LA - eng ER - TY - CPAPER TI - Algebraic models of reasoning AU - Gust, Helmar AU - Schmid, Ute AU - Kühnberger, Kai-Uwe PY - 2003 T2 - Algebraic Models of Reasoning, September 15th-18th, 2003 : a Workshop at the 26th German Conference on Artificial Intelligence, KI 2003, Hamburg ; proceedings SP - 5 - 20 CY - Hamburg UR - https://fis.uni-bamberg.de/handle/uniba/11589 LA - eng ER - TY - CPAPER TI - An algebraic framework for solving proportional and predictive analogies AU - Schmid, Ute AU - Gust, H. AU - Kühnberger, K.-U. AU - Burghardt, J. PY - 2003 T2 - Proceedings of EuroCogSci 03 : the European Cognitive Science Conference 2003, Osnabrück, Germany, 10.-13. September 2003 SP - 295 - 300 CY - Mahwah, NJ u.a., UR - https://fis.uni-bamberg.de/handle/uniba/11580 LA - eng ER - TY - GEN TI - Inductive synthesis of functional programs - Learning domain-specific control rules and abstract schemes AU - Schmid, Ute PY - 2003 PB - Professur Angewandte Informatik / Kognitive Systeme CY - Bamberg UR - https://fis.uni-bamberg.de/handle/uniba/11588 LA - eng ER - TY - BOOK TI - Zum Einfluß von Situationsmodellen auf die Verarbeitung konsistenter versus inkonsistenter Textinformation AU - Durstewitz, Daniel AU - Schmid, Ute AU - Claus, Berry AU - Eyferth, Klaus PY - 1994 PB - TU, Fachbereich 13, Projektgruppe KIT CY - Berlin T3 - KIT-Report / Institut für Software und Theoretische Informatik, Fachbereich 20, Technische Universität Berlin / Projektgruppe KIT, Künstliche Intelligenz und Textverstehen UR - https://fis.uni-bamberg.de/handle/uniba/92876 LA - deu AB - Die vorliegende Untersuchung beschäftigt sich mit der Rolle von Situationsmodellen beim Textverstehen. Unter Situationsmodellen werden allgemein analoge, bisweilen bildhaft-visuelle, Repräsentationen verstanden, die räumliche und funktionale Beziehungen homomorph zu natürlichen Situationen abbilden. Situationsmodellen wird eine entscheidende Rolle bei der Interpretation von Sätzen in Textzusammenhängen, insbesondere bei der Zuweisung von Referenzobjekten zu Ausdrücken (z.B. in der Anaphernresolution), zugesprochen. In Anlehnung an Glenberg, Meyer & Lindem (1987) soll diese Studie die Rolle von Situationsmodellen beim Textverstehen weiter klären. Dazu wurde in kurzen Geschichten, bestehend aus jeweils fünf Sätzen, ein Zielobjekt (Target) entweder mit anderen Objekten oder Agenten im aktuellen Situationsmodell räumlich verbunden ('assoziiert') oder von diesen getrennt ('dissoziiert'). Der letzte (kritische) Satz jeder Geschichte war dann jeweils konsistent oder inkonsistent mit der Lokation des Targets. Erhoben wurden Lesezeiten für den letzten Satz sowie Fehlerraten und Reaktionszeiten bei der Beantwortung eines Behauptungssatzes, der jeder Geschichte folgte. Unsere Hypothese ist, daß unter der Bedingung 'assoziiert' die Lesezeiten für konsistente Sätze kürzer ausfallen als für inkonsistente, daß sich diese Differenz unter der Bedingung 'dissoziiert' aber nicht findet, und begründen dies folgendermaßen: Hängt das Verstehen des kritischen Satzes vom jeweils aktuellen Situationsmodell ab, so führt eine inkonsistente Aussage über die Lokation des Targets nur dann zu Interpretationsschwierigkeiten, wenn dieses auch im Situationsmodell repräsentiert ist. Falls dies, wie für die dissoziierte Bedingung angenommen, nicht mehr der Fall ist, sollten auch inkonsistente Informationen keine Verständnisprobleme bereiten. Unsere Befunde stützen in der Tendenz die Hypothese, jedoch nur für einige der Geschichten. Für diese sind die Unterschiede in den Lesezeiten unter der assoziierten Bedingung größer als unter der dissoziierten. Wegen erheblicher Varianz zwischen den Geschichten wurde das Ergebnis nicht signifikant. Eine Analyse der Fehlerraten ließ einen Haupteffekt des Faktors Konsistenz erkennen: Nach inkonsistenten Schlußsätzen kommt es häufiger zur Fehllokalisierung assoziierter und dissoziierter Objekte. Weitere Untersuchungen, in denen die Konstruktion der Geschichten strengeren Kriterien folgt, damit eindeutigere Schlußfolgerungn möglich sind, sollen folgen. KW - - ER - TY - BOOK TI - Induktion von Perspektive in räumlichen Situationsmodellen in Abhängigkeit vom sprachlichen Ausdruck AU - Fricke, Ellen AU - Durstewitz, Daniel AU - Claus, Berry AU - Schmid, Ute PY - 1994 PB - TU, Fachbereich 13, Projektgruppe KIT CY - Berlin T3 - KIT-Report UR - https://fis.uni-bamberg.de/handle/uniba/91263 LA - deu AB - Es werden zwei Untersuchungen vorgestellt, die auf einer Serie von Experimenten von Franklin, Tversky, Bryant u.a. aufbauen. In diesen Experimenten wurde gezeigt, daß Leser in aufgrund textueller Beschreibungen aufgebauter räumlicher Situationsmodelle unterschiedliche Perspektiven einnehmen, die sich anhand der Verfügbarkeitsmuster von Objekten aus dem Raum differenzieren lassen. Unser Anliegen war es, zu untersuchen, inwieweit die in den Raumbeschreibungen verwendeten deiktischen Lokalisierungsausdrücke und unterschiedliche verbale Ausdrücke bestimmte Perspektiven induzieren, und ob sich unterschiedliche induzierte Perspektiven zur semantischen Differenzierung von Ausdrücken mit Wahrnehmungsverben heranziehen lassen. Unser Textmaterial bestand aus kurzen Geschichten, in denen ein handelnder Protagonist in einem Raum beschrieben wurde. Die Position verschiedener Objekte wurde entweder relativ zum Protagonisten (z.B. "rechts von ... ") oder relativ zur virtuellen Perspektive eines Erzählers (z.B. "An der rechten Wand ... ") festgelegt. In nachfolgenden Sätzen wurden aktive Handlungen des Protagonisten oder passive Wahrnehmungen mit Ausdrücken wie "Er sieht zum...", "Er geht zum ... ", "Er sieht den... " oder "Dort ist ... " beschrieben. Zwar zeigen die Ergebnisse signifikante Unterschiede in den Verfügbarkeitsmustem in Abhängigkeit von der Raumbeschreibung und den verwendeten verbalen Ausdrücken, die auch darauf hindeuten, daß sich semantische Aspekte von Ausdrücken mit Wahrnehmungs- und Handlungsverben unterscheiden lassen, jedoch sind sie inkonsistent zu den von Franklin, Tversky u.a. gefundenen und sind nur schwer interpretierbar. Aus den Reaktionszeitmustern konnte die eingenommene Perspektive nicht eindeutig und konsistent mit verschiedenen theoretischen Vorstellungen ermittelt werden. KW - - ER - TY - JOUR TI - Programmieren lernen : Unterstützung des Erwerbs rekursiver Programmiertechniken durch Beispielfunktionen und Erklärungstexte AU - Schmid, Ute PY - 1994 JO - Kognitionswissenschaft VL - 4 SP - 47-54 PB - Springer CY - Berlin ; Heidelberg [u.a.] SN - 0938-7986 UR - https://fis.uni-bamberg.de/handle/uniba/90972 LA - deu AB - Beim Erwerb von Programmiertechniken ist das Lernen rekursiver Kontrollstrukturen für Anfänger meist die größte Hürde. Die Auswahl von geeignetem Lehrmaterial zur Unterstütznng des Lernprozesses ist deshalb gerade für die Vermittlung rekursiver Programmierung relevant. Es wird eine Studie vorgestellt, in der der Einfluß von zwei Lehrmaterialien - Beispielprogrammen und erklärenden Texten - auf den Erwerb rekursiver Programmiertechniken untersucht wurde. Es zeigte sich, daß Lernen mit Erklärungen und mit Beispielen zu vergleichbaren Transferleistungen führt, die Performanz während des Lernprozesses ist bei Unterstützung durch Erklärungen allerdings wesentlich besser als bei Unterstützung durch Beispiele. KW - Wissenserwerb ER - TY - BOOK TI - Der Einfluß von Beispielähnlichkeit auf induktive Lernprozesse beim rekursiven Programmieren AU - Schmid, Ute AU - Kaup, Barbara PY - 1994 PB - Technische Universität Berlin CY - Berlin T3 - Forschungsberichte aus dem Institut für Psychologie UR - https://fis.uni-bamberg.de/handle/uniba/90966 LA - deu AB - Es wurde eine Untersuchung durchgeführt, bei der geprüft wurde, auf welche Weise der induktive Erwerb von rekursiven Programmiertechniken durch die Ähnlichkeit von Beispiel- und Zielproblem beeinflußt wird. Dabei wurde davon ausgegangen, daß die Art der Beispiele sowohl den Lösungserfolg rekursiver Aufgaben als auch das induzierte Wissen über den neuen Problembereich beeinflussen. Die Beispielähnlichkeit wurde systematisch variiert. Zusätzlich wurde die Wirkung von Vergleichs- und Anpassungsprozessen getrennt erfaßt, indem einer Gruppe von Probanden das Ergebnis des Vergleichsprozesses vorgegeben wurde. 55 Programmieranfänger nahmen an vier aufeinanderfolgenden Tagen jeweils 3 Stunden an der Untersuchung teil. Nach Vermittlung der Syntax einer einfachen funktionalen Sprache, sollten die Probanden am dritten und vierten Tag sechs rekursive Funktionen am Rechner programmieren. Dabei wurde ihnen je ein Beispiel, entsprechend der experimentellen Bedingungen vorgegeben. Geprüft wurde der Einfluß der Lernbedingung auf (1) den Prozeß der Aufgabenlösungen und (2) den resultierenden Wissenserwerb. Der Wissenserwerb wurde dabei zum einen durch einen Abschlußtest erfaßt, bei dem verschiedene Transferaufgaben zu lösen waren. Zum anderen wurde die Schemainduktion explizit erfaßt, indem die Probanden zu drei Zeitpunkten jeweils 28 Funktionen sortieren sollten. Es zeigte sich, daß die Lernbedingung einen bedeutsamen Einfluß auf die Aufgabenlösung hat: Je ähnlicher ein Beispiel zum Zielproblem ist, desto wahrscheinlicher wird die Aufgabe gelöst; die Vorgabe des Vergleichsprozesses führt ebenfalls zu einer erhöhten Lösungswahrscheinlichkeit. Bezüglich des Wissenserwerbs zeigt die Lernbedingung keinen eindeutigen Einfluß. Betrachtet man die Merkmale, nach denen die Probanden sortieren, zeigt sich, daß Probanden, die das Merkmal "Rekursionstyp" zur Klassifikation verwenden, sowohl mehr Aufgaben lösen als auch eine höhere Transferleistung im Abschlußtest zeigen. KW - - ER - TY - CPAPER TI - Der Einfluß von Beispielähnlichkeit auf induktive Lernprozesse beim rekursiven Programmieren AU - Schmid, Ute AU - Kaup, Barbara PY - 1994 T2 - Abstract-Band der 36. Tagung experimentell arbeitender Psychologinnen und Psychologen (36. TeaPP) SP - 268 PB - Ludwig-Maximilians-Universität CY - München UR - https://fis.uni-bamberg.de/handle/uniba/58007 LA - deu AB - - KW - Softwareentwicklung ER - TY - CPAPER TI - Der Einfluß von Beispielähnlichkeit auf induktive Lernprozesse beim rekursiven Programmieren AU - Schmid, Ute AU - Kaup, Barbara PY - 1994 T2 - 39. Kongress der Deutschen Gesellschaft für Psychologie, 25. - 29. September 1994 in Hamburg SP - 625 PB - Psychologisches Inst. I der Univ. CY - Hamburg SN - 3-924330-17-4 UR - https://fis.uni-bamberg.de/handle/uniba/56129 LA - deu AB - . KW - - ER - TY - THES TI - Erwerb rekursiver Programmiertechniken als Induktion von Konzepten und Regeln : ein kognitionswissenschaftlicher Zugang zum Erwerb kognitiver Fertigkeiten AU - Schmid, Ute PY - 1994 PB - Infix CY - Sankt Augustin T3 - Dissertationen zur künstlichen Intelligenz SN - 3-929037-70-X UR - https://fis.uni-bamberg.de/handle/uniba/38151 LA - deu AB - - KW - - ER - TY - BOOK TI - Determinanten des Erwerbs von Programmierkompetenz AU - Schmid, Ute AU - Ulber, Daniela PY - 1993 PB - Technische Universität Berlin CY - Berlin T3 - Forschungsberichte aus dem Institut für Psychologie UR - https://fis.uni-bamberg.de/handle/uniba/93221 LA - deu AB - Es wird eine empirische Untersuchung vorgestellt, bei der der Einfluß von 1) der Art der vorgegebenen Lernhilfe und 2) dem kognitiven Stil von Personen auf das Lösen von rekursiven Programmieraufgaben und den Lerntransfer geprüft wird. Als Lernhilfen werden dabei erklärende Texte, Beispielprogramme oder beide genannten Materialien verwendet. Zudem wurden die untersuchten Personen aufgrund der Differenz zweier Testskalen als induktive und deduktive Denker klassifiziert. Es zeigte sich, daß - abweichend von den formulierten Hypothesen - die Aufgabenlösungen besser durch Erklärungen als durch Beispiele unterstützt werden. Dieser Unterschied resultiert jedoch nicht in Unterschieden bezüglich dem Lerntransfer. Bezüglich des Einflusses der Denkstile ergab sich ebenfalls ein nicht den Hypothesen entsprechendes Ergebnis: Personen mit induktivem Denkstil kommen besser mit Erklärungen, Personen mit deduktivem Stil besser mit Beispielen zurecht. Um genauere Hinweise über den Einfluß verschiedener Lernhilfen auf Aufgabenlösung und Lerntransfer zu erhalten, werden zusätzlich verschiedene Kennwerte zur Erfassung des Hilfeaufrufverhaltens betrachtet. KW - - ER - TY - BOOK TI - Der Einfluß von Lehrmaterial auf das Lösen rekursiver Programmieraufgaben : eine Fehleranalyse AU - Schmid, Ute AU - Gräbener, Jens PY - 1993 PB - Technische Universität Berlin CY - Berlin T3 - Forschungsberichte aus dem Institut für Psychologie UR - https://fis.uni-bamberg.de/handle/uniba/93218 LA - deu AB - In einer Untersuchung zum Erwerb rekursiver Programmiertechniken (Schmid & Ulber 1993) wurde der Einfluß von Lehrmaterialien 1) auf den Lösungserfolg bei Programmieraufgaben und 2) auf den Lerntransfer geprüft. Als Lehrmaterialien wurden dabei 1) erklärende Texte zu den Aufgaben, 2) Beispielfunktionen und 3) beide Materialien verwendet. Es zeigte sich, daß alle drei Lernbedingungen zu vergleichbarem Lerntransfer führen. Bezüglich des Lösungserfolges bei den Programmieraufgaben ergibt sich jedoch ein bedeutsamer Nachteil für die Probanden, die nur Beispielfunktionen zur Verfügung haben. Um genaueren Aufschluß über die Wirkung von Beispielfunktionen auf das Lösen von Aufgaben zu erhalten, wurde einer Fehleranalyse durchgeführt. Dabei wird deutlich, daß Programmieranfänger noch keine adäquaten Regeln zur Verfügung haben, um Beispielfunktionen auf Aufgaben zu übertragen: Es werden häufig gerade die Anteile der Beispiele übernommen, die an die Aufgabe hätten angepaßt werden müssen, gleichbleibende Teile werden dagegen nicht als solche erkannt. Dieses Vorgehen führt zu einem hohen Anteil an semantischen Fehlern, vor allem zu nicht-terminierenden Lösungen. Dagegen produzieren Probanden, die nur mit erklärenden Texten oder beiden Materialien arbeiten häufig schnell semantisch korrekte Lösungen, die allerdings syntaktische Fehler enthalten. Lediglich die vor allem von der Beispielgruppe erzeugten Fehler stehen jedoch in einem Zusammenhang mit dem Lösungserfolg bei den Aufgaben. KW - - ER - TY - CPAPER TI - Erwerb rekursiver Programmiertechniken als Induktion von Konzepten und Regeln AU - Schmid, Ute AU - Kaup, Barbara PY - 1993 T2 - KI-94 Workshops : 18. Deutsche Jahrestagung für Künstliche Intelligenz, KI-94, Saarbrücken, 18. - 23. September 1994 ; Extended abstracts SP - 418-419 PB - Gesellschaft für Informatik CY - Bonn UR - https://fis.uni-bamberg.de/handle/uniba/90970 LA - deu AB - - KW - Studie ER - TY - CPAPER TI - Erwerb rekursiver Programmiertechniken aus Beispielfunktionen und Erklärungen AU - Schmid, Ute PY - 1993 T2 - Abstract-Band der 35. Tagung experimentell arbeitender Psychologen SP - 247 PB - Westfälische Wilhelms-Universität CY - Münster UR - https://fis.uni-bamberg.de/handle/uniba/58011 LA - deu AB - - KW - Studie ER - TY - JOUR TI - Zur Invarianz von Problemlösestilen über verschiedene Bereiche AU - Andresen, Norbert AU - Schmid, Ute PY - 1993 JO - Zeitschrift für experimentelle und angewandte Psychologie : Organ der Deutschen Gesellschaft für Psychologie VL - 40 IS - 1 SP - 1-17 PB - Verl. für Psychologie Hogrefe CY - Göttingen SN - 0044-2712 UR - https://fis.uni-bamberg.de/handle/uniba/56042 LA - deu AB - Um zu prüfen, ob individuelle Problemlösestile über verschiedene Problembereiche hinweg invariante Merkmale aufweisen, wurden Probanden mit zwei sehr verschiedenen komplexen Aufgaben konfrontiert. Personen, deren unterschiedliches Arbeitsverhalten an einem CAD-System analysiert wurde, konnten zwei Jahre später dazu gewonnen werden, ein einfaches dynamisches System zu regeln. Für die CAD-Untersuchung wurden aus den Eingaben zur Erledigung einer Zeichenaufgabe quantitative Benutzerkennwerte ermittelt. Bei dem einfachen dynamischen System handelt es sich um die schon mehrfach publizierte Kühlhaus-Aufgabe. Diese wurde in zwei Durchgängen bearbeitet. Es wurden Kennwerte für den Problemlösungsverlauf und die Lösungsgüte entwickelt. Zusätzlich wurden ein Maß der Allgemeinen Intelligenz und das über das System erworbene Wissen erhoben. Es stellten sich bedeutsame Zusammenhänge zwischen den Kennwerten für die zweite Systemregelung und den übrigen Variablen heraus: Verlaufsmerkmale der zweiten Regelung lassen sich aus dem Verlauf der ersten Regelung vorhersagen. Steuerungsgüte und erworbenes Systemwissen werden durch Merkmale der individuellen CAD-Problemlösungen vorhergesagt. Die Allgemeine Intelligenz ist dagegen, wie in vielen Untersuchungen bestätigt, kein tauglicher Prädiktor für komplexes Problemlöseverhalten. KW - - ER - TY - BOOK TI - A method for analyzing computer users' behavior sequences AU - Schmid, Ute AU - Konerding, Uwe PY - 1992 PB - Technische Universität Berlin CY - Berlin T3 - Forschungsberichte aus dem Institut für Psychologie UR - https://fis.uni-bamberg.de/handle/uniba/92880 LA - eng AB - This paper presents a formal approach to analyzing behavioral sequences produced by computer users. Following this approach, the behavioral sequences are represented as square transition matrices, distances between the individual matrices are calculated, and the resulting distance matrix is scaled multidimensionally. The emerging scales reflect differences in the users' problem solving behavior and can be used as a guideline for detecting behavioral aspects influencing quality of task solution. The method was exemplarily applied to two different kinds of behavioral data, the first reported by Upmeyer, Meseke & Enzmann (1988) and the second by Eyferth, Widowski & Schmid (1991). KW - cornputer user KW - behavior sequences KW - multidimensional scaling ER - TY - JOUR TI - Deskription und Analyse komplexer Verhaltenssequenzen : Benutzerstrategien beim Arbeiten mit CAD-Systemen AU - Schmid, Ute AU - Meseke, Bodo PY - 1991 JO - Zeitschrift für experimentelle und angewandte Psychologie : Organ der Deutschen Gesellschaft für Psychologie VL - 38 IS - 2 SP - 307-320 PB - Verl. für Psychologie Hogrefe CY - Göttingen SN - 0044-2712 UR - https://fis.uni-bamberg.de/handle/uniba/56044 LA - deu AB - Es wird ein Verfahren vorgestellt, das es ermöglicht, Eingabesequenzen von Computeranwendern bei der Lösung einer komplexen Aufgabe zu vergleichen. Die individuellen Sequenzen werden in Markov-Ketten erster Ordnung umgewandelt. Die Ahnlichkeit dieser quadratischen Matrizen kann dann über die Abweichungen der Zellenwerte ermittelt werden. Es resultiert eine symmetrische Matrix der Sequenzdistanzen, die zu weiteren quantitativen Analysen (z.B. multidimensionale Skalierung) verwendet werden kann. Das Verfahren wird auf den Vergleich von Eingabeprotokollen bei der Arbeit mit einem CAD-System angewendet, um Hinweise auf unterschiedliche Benutzertypen zu erhalten. Die Sequenzunterschiede konnten auf zwei für die Arbeitseffektivität bedeutsame Benutzermerkmale - "adäquate Befehlsrepräsentation" und "Arbeitsstil" - zurückgeführt werden. KW - - ER - TY - CPAPER TI - Deskription und Analyse komplexer Verhaltenssequenzen : Benutzerstrategien beim Arbeiten mit CAD-Systemen AU - Schmid, Ute PY - 1990 T2 - 32. Tagung experimentell arbeitender Psychologen, 9. bis 12. April 1990 : Abstracts SP - 44 PB - Universität CY - Regensburg UR - https://fis.uni-bamberg.de/handle/uniba/58014 LA - deu AB - - KW - Studie ER - TY - CPAPER TI - Transfer beim Umgang mit einem einfachen dynamischen System AU - Andresen, Norbert AU - Schmid, Ute PY - 1990 T2 - Bericht über den 37. Kongreß der Deutschen Gesellschaft für Psychologie in Kiel 1990 SP - 2-3 PB - Hogrefe CY - Göttingen ; Toronto ; Zürich SN - 3-8017-0416-5 UR - https://fis.uni-bamberg.de/handle/uniba/56131 LA - deu AB - . KW - - ER -