Strategies for Safety Goal Decomposition for Neural Networks
Schwalbe, Gesina; Schels, Martin (2019): Strategies for Safety Goal Decomposition for Neural Networks, in: München: German Chapter of the ACM e.V.
Details
- Fakultät/Lehrstuhl
- Autorin(nen)/Autor(en)
- Schwalbe, GesinaSchels, Martin
- Konferenz
- 3rd ACM Computer Science in Cars Symposium – Future Challenges in Artificial Intelligence & Security for Autonomous Vehicles, Kaiserslautern
- Verlagsangabe
- German Chapter of the ACM e.V. : München
- Erscheinungsjahr
- 2019
- Seiten
- 3
- Sprache(n)
- Englisch
- Abstract
Neural networks (NNs) have become a key technology for solving highly complex tasks, and require integration into future safety argumentations. New safety relevant aspects introduced by NN based algorithms are: representativity of test cases, robustness, inner representation and logic, and failure detection for NNs. In this paper, a general argumentation structure for safety cases respecting these four aspects is proposed together with possible sources of evidence.
- GND-Schlagwort(e)
- Neuronales Netz ; Beweisführung ; Dekomposition ; Sicherheit
- Freie Schlagwort(e)
- neural networksafety argumentationsafety goal decomposition
- DDC-Klassifikation
- 004 Computer science
- RVK-Klassifikation
- ST 301
- Dokumenttyp
- Konferenzveröffentlichung
- URI
- Datum der Freischaltung
- 10.05.2022