User: Guest  Login
Title:

Neural Networks for Safety-Critical Applications - Challenges, Experiments and Perspectives

Document type:
Konferenzbeitrag
Author(s):
Cheng, Chih-Hong; Diehl, Frederik; Hinz, Gereon; Hamza, Yassine; Nührenberg, Georg; Rickert, Markus; Rueß, Harald; Truong-Le, Michael
Abstract:
We propose a methodology for designing dependable Artificial Neural Networks (ANNs) by extending the concepts of understandability, correctness, and validity that are crucial ingredients in existing certification standards. We apply the concept in a concrete case study for designing a highway ANN-based motion predictor to guarantee safety properties such as impossibility for the ego vehicle to suggest moving to the right lane if there exists another vehicle on its right.
Book / Congress title:
Proceedings of the Design, Automation & Test in Europe Conference & Exhibition (DATE)
Year:
2018
Month:
Mar
Pages:
1005--1006
Fulltext / DOI:
doi:10.23919/DATE.2018.8342158
 BibTeX