Zusammenfassung The market potential of safety critical products using AI is very attractive and Deep Learning Neural Networks (NN) have proven strengths to provide important functionality. This paper describes some of the challenges in arguing safety of systems using Deep Learning NN, especially functional improvement in context of SOTIF (Safety of the Intended Functionality) or other approaches to provide the safety case. An architecture and independence controller is proposed which can be used beneficially to reduce residual risk of functional insufficiencies for Deep Learning NN based systems.
Architecture and independence controller for deep learning in safety critical applications
2019-01-01
12 pages
Article/Chapter (Book)
Electronic Resource
German
Monoprocessed computer architecture for safety critical applications
British Library Conference Proceedings | 2002
|DACAPO: A Distributed Computer Architecture for Safety-Critical Control Applications
British Library Conference Proceedings | 1995
|A Fault-Tolerant Processor Core Architecture for Safety-Critical Automotive Applications
British Library Conference Proceedings | 2005
|