Zum Inhalt springen

Nur-Lesen-Fassung: Das Forschungsinformationssystem (FIS) ist aus Sicherheitsgründen vorübergehend durch diese Nur-Lesen-Fassung ersetzt. Alle öffentlichen Inhalte und Volltexte sind weiterhin abrufbar; Anmeldung, Bearbeitung, Einreichung und Statistiken stehen nicht zur Verfügung. Bei Fragen: fis@uni-bamberg.de

Start › Publikationen › Enhancing Explanatory Interactive Machine Learning : A Generalization of the CAIPI Algorithm

Publikation

Enhancing Explanatory Interactive Machine Learning : A Generalization of the CAIPI Algorithm

Slany, Emanuel (2025): Enhancing Explanatory Interactive Machine Learning : A Generalization of the CAIPI Algorithm, Bamberg: Otto-Friedrich-Universität, doi: 10.20378/irb-107376.

Details

Fakultät/Lehrstuhl
Autorin(nen)/Autor(en)
Verlagsangabe
Otto-Friedrich-Universität : Bamberg
Erscheinungsjahr
2025
Seiten
XXV, 148, Illustrationen, Diagramme, Tabellen
Gutachterin(nen)/Gutachter
Sprache(n)
Englisch
Anmerkungen

Dissertation, Otto-Friedrich-Universität Bamberg, 2025

DOI
Lizenz
URN
Abstract

An inherent challenge of statistical machine learning models is the possibility of erroneous outcomes, which underscores the importance of corrigibility, particularly in sensitive domains. Advances in the field of explainable Artificial Intelligence have revealed that machine learning models might conduct correct decisions based on incorrect decision-making mechanisms. The possibility of detecting erroneous decision making does not prevent incorrect decision-making mechanisms, which is why the research field explanatory interactive machine learning has equipped researchers with the opportunity to revise explanations. Explanatory interactive machine learning procedures vary in their feedback injection mechanism: Some utilize model-specific internals, e.g., they penalize gradients in indecisive regions. Others are model-agnostic and induce additional training data, termed counterexamples, which only contain the relation of human explanation revisions and the target. CAIPI, the origin of the latter category, is an algorithmic framework to optimize machine learning models that iteratively combines components to predict, explain, and interact with instances. It generates counterexamples in iterations with correct prediction and erroneous decision-making mechanism. CAIPI, despite being claimed to be model-agnostic, has been proposed as a theoretical concept, which does not transfer well to practical application scenarios beyond image and text classification. Moreover, its formalization requires refinement, particularly when evaluating the impact of counterexamples on the optimization framework. This thesis aims to address CAIPI’s limitations through a formal analysis of how counterexamples influence the iterative optimization of machine learning models, together with algorithmic modifications of the original CAIPI framework.

GND-Schlagwort(e)
Erklärbare künstliche Intelligenz
Maschinelles Lernen
Computerunterstütztes Lernen
Algorithmus
Freie Schlagwort(e)
Explanatory Interactive Machine Learning
Explainable Artificial Intelligence
Interactive Learning
Machine Learning
CAIPI
DDC-Klassifikation
004 Computer science
RVK-Klassifikation
ST 300
Dokumenttyp
Dissertation
URI
Datum der Freischaltung
13.05.2025

Permalink: https://fis.uni-bamberg.de/handle/uniba/107376 · Daten als JSON · Zitieren: BibTeX · RIS

Datenstand: 16.11.2026

Eingeschränkter Lesezugriff: Anmeldung, Bearbeitung und Einreichung sind vorübergehend deaktiviert.