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

Autor:	Axel Brando, Isabel Serra, Enrico Mezzetti, Francisco J. Cazorla, Jon Perez-Cerrolaza, Jaume Abella
Přispěvatelé:	Barcelona Supercomputing Center
Jazyk:	angličtina
Rok vydání:	2023
Předmět:	Neural networks (Computer science) Redundancy General Computer Science Deep learning (Machine learning) Embedded systems Intel·ligència artificial Informàtica::Intel·ligència artificial [Àrees temàtiques de la UPC] Deep learning Safety Contingency management Neural networks
Popis:	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. The research leading to these results has received funding from the European Research Council (ERC) grant agreement No. 772773 (SuPerCom), the Horizon Europe Programme under the SAFEXPLAIN Project (www.safexplain.eu), grant agreement num.101069595, and the Spanish Ministry of Science and Innovation under grant PID2019-107255GBC21/AEI/10.13039/501100011033.
Databáze:	OpenAIRE
Externí odkaz:	https://explore.openaire.eu/search/publication?articleId=doi_dedup___::143b86d2ab963031f7d977ed438a4d0b https://hdl.handle.net/2117/387765 Zobrazit plný text záznamu