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

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...

ver descrição completa

Detalhes bibliográficos
Autores: Brando, Axel, Serra, Isabel, Mezzetti, Enrico|||0000-0002-1886-2931, Cazorla Almeida, Francisco Javier, Perez Cerrolaza, Jon, Abella Ferrer, Jaume|||0000-0001-7951-4028
Tipo de documento: artigo
Data de publicação:2023
País:España
Recursos:Universitat Politècnica de Catalunya (UPC)
Repositório:UPCommons. Portal del coneixement obert de la UPC
Idioma:inglês
OAI Identifier:oai:upcommons.upc.edu:2117/387765
Acesso em linha:https://hdl.handle.net/2117/387765
https://dx.doi.org/10.1109/MC.2023.3236523
Access Level:Acceso aberto
Palavra-chave:Deep learning (Machine learning)
Neural networks (Computer science)
Deep learning
Redundancy
Neural networks
Safety
Embedded systems
Contingency management
Intel·ligència artificial
Àrees temàtiques de la UPC::Informàtica::Intel·ligència artificial
id ES_d2067d356293deaa72856e46328cdca1
oai_identifier_str oai:upcommons.upc.edu:2117/387765
network_acronym_str ES
network_name_str España
repository_id_str
spelling On Neural Networks Redundancy and Diversity for Their Use in Safety-Critical SystemsBrando, AxelSerra, IsabelMezzetti, Enrico|||0000-0002-1886-2931Cazorla Almeida, Francisco JavierPerez Cerrolaza, JonAbella Ferrer, Jaume|||0000-0001-7951-4028Deep learning (Machine learning)Neural networks (Computer science)Deep learningRedundancyNeural networksSafetyEmbedded systemsContingency managementIntel·ligència artificialÀrees temàtiques de la UPC::Informàtica::Intel·ligència artificialAn 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.Peer ReviewedInstitute of Electrical and Electronics Engineers (IEEE)20232023-05-0120232023-05-23journal articlehttp://purl.org/coar/resource_type/c_6501AMhttp://purl.org/coar/version/c_ab4af688f83e57aainfo:eu-repo/semantics/articleapplication/pdfhttps://hdl.handle.net/2117/387765https://dx.doi.org/10.1109/MC.2023.3236523reponame:UPCommons. Portal del coneixement obert de la UPCinstname:Universitat Politècnica de Catalunya (UPC)InglésengEuropean Commission http://doi.org/10.13039/100010661 Horizon 2020 Framework Programme 772773 Sustainable Performance for High-Performance Embedded Computing SystemsAgencia Estatal de Investigación http://doi.org/10.13039/501100011033 Plan Estatal de Investigación Científica y Técnica y de Innovación 2017-2020 PID2019-107255GB-C21 BSC - COMPUTACION DE ALTAS PRESTACIONES VIIIEuropean Commission http://doi.org/10.13039/501100000780 HE 101069595 SAFE AND EXPLAINABLE CRITICAL EMBEDDED SYSTEMS BASED ON AIopen accesshttp://purl.org/coar/access_right/c_abf2info:eu-repo/semantics/openAccessoai:upcommons.upc.edu:2117/3877652026-05-27T15:37:01Z
dc.title.none.fl_str_mv On Neural Networks Redundancy and Diversity for Their Use in Safety-Critical Systems
title On Neural Networks Redundancy and Diversity for Their Use in Safety-Critical Systems
spellingShingle On Neural Networks Redundancy and Diversity for Their Use in Safety-Critical Systems
Brando, Axel
Deep learning (Machine learning)
Neural networks (Computer science)
Deep learning
Redundancy
Neural networks
Safety
Embedded systems
Contingency management
Intel·ligència artificial
Àrees temàtiques de la UPC::Informàtica::Intel·ligència artificial
title_short On Neural Networks Redundancy and Diversity for Their Use in Safety-Critical Systems
title_full On Neural Networks Redundancy and Diversity for Their Use in Safety-Critical Systems
title_fullStr On Neural Networks Redundancy and Diversity for Their Use in Safety-Critical Systems
title_full_unstemmed On Neural Networks Redundancy and Diversity for Their Use in Safety-Critical Systems
title_sort On Neural Networks Redundancy and Diversity for Their Use in Safety-Critical Systems
dc.creator.none.fl_str_mv Brando, Axel
Serra, Isabel
Mezzetti, Enrico|||0000-0002-1886-2931
Cazorla Almeida, Francisco Javier
Perez Cerrolaza, Jon
Abella Ferrer, Jaume|||0000-0001-7951-4028
author Brando, Axel
author_facet Brando, Axel
Serra, Isabel
Mezzetti, Enrico|||0000-0002-1886-2931
Cazorla Almeida, Francisco Javier
Perez Cerrolaza, Jon
Abella Ferrer, Jaume|||0000-0001-7951-4028
author_role author
author2 Serra, Isabel
Mezzetti, Enrico|||0000-0002-1886-2931
Cazorla Almeida, Francisco Javier
Perez Cerrolaza, Jon
Abella Ferrer, Jaume|||0000-0001-7951-4028
author2_role author
author
author
author
author
dc.subject.none.fl_str_mv Deep learning (Machine learning)
Neural networks (Computer science)
Deep learning
Redundancy
Neural networks
Safety
Embedded systems
Contingency management
Intel·ligència artificial
Àrees temàtiques de la UPC::Informàtica::Intel·ligència artificial
topic Deep learning (Machine learning)
Neural networks (Computer science)
Deep learning
Redundancy
Neural networks
Safety
Embedded systems
Contingency management
Intel·ligència artificial
Àrees temàtiques de la UPC::Informàtica::Intel·ligència artificial
description 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.
publishDate 2023
dc.date.none.fl_str_mv 2023
2023-05-01
2023
2023-05-23
dc.type.none.fl_str_mv journal article
http://purl.org/coar/resource_type/c_6501
AM
http://purl.org/coar/version/c_ab4af688f83e57aa
dc.type.openaire.fl_str_mv info:eu-repo/semantics/article
format article
dc.identifier.none.fl_str_mv https://hdl.handle.net/2117/387765
https://dx.doi.org/10.1109/MC.2023.3236523
url https://hdl.handle.net/2117/387765
https://dx.doi.org/10.1109/MC.2023.3236523
dc.language.none.fl_str_mv Inglés
eng
language_invalid_str_mv Inglés
language eng
dc.relation.none.fl_str_mv European Commission http://doi.org/10.13039/100010661 Horizon 2020 Framework Programme 772773 Sustainable Performance for High-Performance Embedded Computing Systems
Agencia Estatal de Investigación http://doi.org/10.13039/501100011033 Plan Estatal de Investigación Científica y Técnica y de Innovación 2017-2020 PID2019-107255GB-C21 BSC - COMPUTACION DE ALTAS PRESTACIONES VIII
European Commission http://doi.org/10.13039/501100000780 HE 101069595 SAFE AND EXPLAINABLE CRITICAL EMBEDDED SYSTEMS BASED ON AI
dc.rights.none.fl_str_mv open access
http://purl.org/coar/access_right/c_abf2
dc.rights.openaire.fl_str_mv info:eu-repo/semantics/openAccess
rights_invalid_str_mv open access
http://purl.org/coar/access_right/c_abf2
eu_rights_str_mv openAccess
dc.format.none.fl_str_mv application/pdf
dc.publisher.none.fl_str_mv Institute of Electrical and Electronics Engineers (IEEE)
publisher.none.fl_str_mv Institute of Electrical and Electronics Engineers (IEEE)
dc.source.none.fl_str_mv reponame:UPCommons. Portal del coneixement obert de la UPC
instname:Universitat Politècnica de Catalunya (UPC)
instname_str Universitat Politècnica de Catalunya (UPC)
reponame_str UPCommons. Portal del coneixement obert de la UPC
collection UPCommons. Portal del coneixement obert de la UPC
repository.name.fl_str_mv
repository.mail.fl_str_mv
_version_ 1869420314004291584
score 15,300719

Registros relacionados