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.


    Zugriff

    Zugriff prüfen

    Verfügbarkeit in meiner Bibliothek prüfen

    Bestellung bei Subito €


    Exportieren, teilen und zitieren



    Titel :

    Challenges in Using Neural Networks in Safety-Critical Applications


    Beteiligte:


    Erscheinungsdatum :

    11.10.2020


    Format / Umfang :

    563628 byte





    Medientyp :

    Aufsatz (Konferenz)


    Format :

    Elektronische Ressource


    Sprache :

    Englisch



    Safety-Critical Challenges in the Networked Vehicle

    Hanebeck, Jochen | Springer Verlag | 2016



    Challenges in Validating Safety-Critical Embedded Systems

    Feiler, Peter H. | SAE Technical Papers | 2009