Litcius/Paper detail

Challenges in Using Neural Networks in Safety-Critical Applications

Håkan Forsberg, Joakim Lindén, Johan Hjorth, Torbjörn Månefjord, Masoud Daneshtalab

202018 citationsDOI

Abstract

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.

Topics & Concepts

ImplementationComputer scienceFunction (biology)Life-critical systemArtificial neural networkSystem safetyRisk analysis (engineering)Work (physics)Systems engineeringSoftware engineeringArtificial intelligenceReliability engineeringEngineeringSoftwareProgramming languageMedicineMechanical engineeringBiologyEvolutionary biologyAdversarial Robustness in Machine LearningAnomaly Detection Techniques and ApplicationsFault Detection and Control Systems
Challenges in Using Neural Networks in Safety-Critical Applications | Litcius