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: Bamberg: Otto-Friedrich-Universität, doi: 10.20378/irb-47275.
Details
- Fakultät/Lehrstuhl
- Autorin(nen)/Autor(en)
- Schwalbe, GesinaSchels, Martin
- Herausgebende Institution
- European Congress on Embedded Real Time Software and Systems (ERTS), 10, 2020, Toulouse
- Verlagsangabe
- Otto-Friedrich-Universität : Bamberg
- Erscheinungsjahr
- 2020
- Seiten
- 11
- Quelle/Weitere Ausgabe
- European Congress on Embedded Real Time Software and Systems (ERTS) / European Congress on Embedded Real Time Software and Systems (ERTS) (Hg.) – Toulouse : ERTS, 2020, S. 11
- Sprache(n)
- Englisch
- DOI
- Lizenz
- URN
- 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-Schlagwort(e)
- ISO/DIS 26262FunktionssicherheitMaschinelles LernenKünstliche Intelligenz
- Freie Schlagwort(e)
- functional safetylife-cycleISO 26262machine learningexplainable AI
- DDC-Klassifikation
- 004 Computer science
- RVK-Klassifikation
- ST 300
- Peer Reviewed
- ja
- Internationale Verbreitung
- ja
- Open-Access-Zeitschrift
- ja
- Dokumenttyp
- Konferenzveröffentlichung
- URI
- Datum der Freischaltung
- 03.07.2020