In this paper, we discuss challenges when using neural networks (NNs) in safety-critical applications. We address the challenges one by one, with aviation safety in mind. We then introduce a possible implementation to overcome the challenges. Only a small portion of the solution has been implemented physically and much work is considered as future work. Our current understanding is that a real implementation in a safety-critical system would be extremely difficult. Firstly, to design the intended function of the NN, and secondly, designing monitors needed to achieve a deterministic and fail-safe behavior of the system. We conclude that only the most valuable implementations of NNs should be considered as meaningful to implement in safety-critical systems.
Challenges in Using Neural Networks in Safety-Critical Applications
2020-10-11
563628 byte
Conference paper
Electronic Resource
English
Safety-Critical Challenges in the Networked Vehicle
Springer Verlag | 2016
|Challenges in updating military safety-critical hardware
IEEE | 2009
|Challenges in Validating Safety-Critical Embedded Systems
SAE Technical Papers | 2009
|Challenges in updating military safety-critical hardware
IEEE | 2010
|Safety and security profiles of industry networks used in safety- critical applications
DOAJ | 2008
|