On Neural Networks Redundancy and Diversity for Their Use in Safety-Critical Systems

Axel Brando, Isabel Serra, Enrico Mezzetti, Francisco J. Cazorla, Jon Pérez-Cerrolaza, Jaume Abella

Abstract

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.
BibTeX
@article{brando2023neural,
  author = {Axel Brando and Isabel Serra and Enrico Mezzetti and Francisco J. Cazorla and Jon Pérez-Cerrolaza and Jaume Abella},
  title = {{On Neural Networks Redundancy and Diversity for Their Use in Safety-Critical Systems}},
  journal = {Computer},
  year = {2023},
  doi = {10.1109/mc.2023.3236523},
}
Figure