A Survey on Methods for the Safety Assurance of Machine Learning Based Systems
Schwalbe, Gesina; Schels, Martin (2020): A Survey on Methods for the Safety Assurance of Machine Learning Based Systems, in: Proceeding of the 10th European Congress on Embedded Real Time Software and Systems, Toulouse.
Details
- Faculty/Chair
- Faculty/Professorship
- Author
- Schwalbe, GesinaSchels, Martin
- Title of the compilation
- Proceeding of the 10th European Congress on Embedded Real Time Software and Systems
- Corporate Body
- European Congress on Embedded Real Time Software and Systems (ERTS),10, 2020, Toulouse
- Year of publication
- 2020
- Pages
- 11
- Language
- English
- URL
- Abstract
Methods for safety assurance suggested by the ISO 26262 automotive functional safety standard are not sufficient for applications based on machine learning (ML). We provide a structured, certification oriented overview on available methods supporting the safety argumen-tation of a ML based system. It is sorted into life-cycle phases, and maturity of the approach as well as applicability to different ML types are collected. From this we deduce current open challenges: powerful solvers, inclusion of expert knowledge, validation of data representativity and model diversity, and model introspection with provable guarantees.
- GND Keywords
- ISO/DIS 26262 ; Funktionssicherheit ; Maschinelles Lernen ; Künstliche Intelligenz
- Keywords
- functional safetylife-cycleISO 26262machine learningexplainable AI
- DDC Classification
- 004 Computer science
- RVK Classification
- ST 300
- Type
- Conferenceobject
- URI
- Activation date
- 2020-03-11