On Neural Networks Redundancy and Diversity for Their Use in Safety-Critical Systems
Axel Brando, Isabel Serra, Enrico Mezzetti, Francisco Javier Cazorla, Jon Perez-Cerrolaza, Jaume Abella · Computer · 2023
An increasing number of critical functionalities integrated in embedded critical systems rely on deep learning (DL) technology. This article summarizes certain key aspects of DL’s intrinsic stochastic and training-data-dependent nature that are at odds with current domain-specific functional safety standards. We exemplify how redundancy and diversity of neural networks can help to reconcile DL technology and functional safety requirements.