Assuring Safety-Critical Machine Learning-Enabled Systems: Challenges and Promise

Assuring Safety-Critical Machine Learning-Enabled Systems: Challenges and Promise

We outline how assurance processes work for conventional systems and identify the primary difficulty in applying them to machine learning-enabled systems. We then outline a path forward, identifying where considerable research remains.

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:Computer (Long Beach, Calif.) Calif.), 2023-09, Vol.56 (9), p.83-88
Hauptverfasser: Goodloe, Alwyn E., Laplante, Phil
Format: Artikel
Sprache:eng
Schlagworte:
Machine learning
Quality assurance
Safety critical
Safety management
Online-Zugang:Volltext bestellen
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Beschreibung
Zusammenfassung:We outline how assurance processes work for conventional systems and identify the primary difficulty in applying them to machine learning-enabled systems. We then outline a path forward, identifying where considerable research remains.
ISSN:0018-9162
1558-0814
DOI:10.1109/MC.2023.3266860