Detecting hard synapses faults in artificial neural networks

This paper presents the concepts of detecting hard faults in artificial neural network synapses using the modification of the neural network settings. The core of this work is based on weights values modification and inserting the chosen testing data when comparing the neural network output to the k...

Full description

Saved in:
Bibliographic Details
Published in2019 IEEE Latin American Test Symposium (LATS) pp. 1 - 6
Main Authors Krcma, Martin, Kotasek, Zdenek, Lojda, Jakub
Format Conference Proceeding
LanguageEnglish
Published IEEE 01.03.2019
Subjects
Online AccessGet full text

Cover

Loading…
Abstract This paper presents the concepts of detecting hard faults in artificial neural network synapses using the modification of the neural network settings. The core of this work is based on weights values modification and inserting the chosen testing data when comparing the neural network output to the known valid results. The paper also discusses the problem of neural networks output saturation and provides experiments regarding an influence of the neural network settings to the problem.
AbstractList This paper presents the concepts of detecting hard faults in artificial neural network synapses using the modification of the neural network settings. The core of this work is based on weights values modification and inserting the chosen testing data when comparing the neural network output to the known valid results. The paper also discusses the problem of neural networks output saturation and provides experiments regarding an influence of the neural network settings to the problem.
Author Krcma, Martin
Kotasek, Zdenek
Lojda, Jakub
Author_xml – sequence: 1
  givenname: Martin
  surname: Krcma
  fullname: Krcma, Martin
  organization: Faculty of Information Technology, IT4Innovations, Centre of Excellence, Brno University of Technology, Brno, 612 66, Czech Republic
– sequence: 2
  givenname: Zdenek
  surname: Kotasek
  fullname: Kotasek, Zdenek
  organization: Faculty of Information Technology, IT4Innovations, Centre of Excellence, Brno University of Technology, Brno, 612 66, Czech Republic
– sequence: 3
  givenname: Jakub
  surname: Lojda
  fullname: Lojda, Jakub
  organization: Faculty of Information Technology, IT4Innovations, Centre of Excellence, Brno University of Technology, Brno, 612 66, Czech Republic
BookMark eNotj81KAzEURiPoQmsfQNzkBWa8maRzE3BT6i8MdDPQZclMbjQ4piVJkb69Rbs68C0O37lhl3EXibE7AbUQYB66Zb-pGxCm1giqlXjB5ga1wEYLgYsWrtnjExUaS4gf_NMmx_Mx2n2mzL09TCXzELlNJfgwBjvxSIf0h_KzS1_5ll15O2Wanzlj_ctzv3qruvXr-2rZVcFAqZBOD9ADmlERSnAAvhmohVHrxikHCAYBSMn2NILzfnDDQg_KN1o7oeWM3f9rAxFt9yl823TcnpPkL6BSRSQ
ContentType Conference Proceeding
DBID 6IE
6IL
CBEJK
RIE
RIL
DOI 10.1109/LATW.2019.8704637
DatabaseName IEEE Electronic Library (IEL) Conference Proceedings
IEEE Proceedings Order Plan All Online (POP All Online) 1998-present by volume
IEEE Xplore All Conference Proceedings
IEEE Electronic Library Online
IEEE Proceedings Order Plans (POP All) 1998-Present
DatabaseTitleList
Database_xml – sequence: 1
  dbid: RIE
  name: IEEE Xplore
  url: https://proxy.k.utb.cz/login?url=https://ieeexplore.ieee.org/
  sourceTypes: Publisher
DeliveryMethod fulltext_linktorsrc
EISBN 9781728117560
1728117569
EndPage 6
ExternalDocumentID 8704637
Genre orig-research
GroupedDBID 6IE
6IL
CBEJK
RIE
RIL
ID FETCH-LOGICAL-i90t-7e0197f079c4e730d00f2be60c882d4d0709700e436e600dffbdb58b4f288d183
IEDL.DBID RIE
IngestDate Mon Nov 04 11:48:14 EST 2024
IsPeerReviewed false
IsScholarly false
Language English
LinkModel DirectLink
MergedId FETCHMERGED-LOGICAL-i90t-7e0197f079c4e730d00f2be60c882d4d0709700e436e600dffbdb58b4f288d183
PageCount 6
ParticipantIDs ieee_primary_8704637
PublicationCentury 2000
PublicationDate 2019-March
PublicationDateYYYYMMDD 2019-03-01
PublicationDate_xml – month: 03
  year: 2019
  text: 2019-March
PublicationDecade 2010
PublicationTitle 2019 IEEE Latin American Test Symposium (LATS)
PublicationTitleAbbrev LATW
PublicationYear 2019
Publisher IEEE
Publisher_xml – name: IEEE
Score 1.7337363
Snippet This paper presents the concepts of detecting hard faults in artificial neural network synapses using the modification of the neural network settings. The core...
SourceID ieee
SourceType Publisher
StartPage 1
SubjectTerms Biological neural networks
Hardware
Neurons
Redundancy
Synapses
Task analysis
Title Detecting hard synapses faults in artificial neural networks
URI https://ieeexplore.ieee.org/document/8704637
hasFullText 1
inHoldings 1
isFullTextHit
isPrint
link http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwjV1LSwMxEA5tT55UWvFNDh5Nm91kkw14ER8UseKhYm9lk0ygKNvi7h7015tka0Xx4ClhCCSTmWGGzDcThM604AVVjpEEMkY40IxoIYFQpRMnCybyCKKZPIjxE7-bZbMOOt_UwgBABJ_BMExjLt8uTROeykZet7hgsou6Uqm2VmudqEyoGt1fTp8DVssLv13348OU6C9ut9Hka6cWJvIybGo9NB-_mjD-9yg7aPBdmYcfNz5nF3Wg7KOLawipAE_AoYYKV-9lsaqgwq5oXusKL0ocFKTtFYFDB8s4RPx3NUDT25vp1Zisf0UgC0VrIsFzKB2VynDw5mkpdakGQY2PlS233oSVpBQ4E55IrXPa6izX3KV5br0B76FeuSxhH-GUMhBW58IWkvuwSLNEG5UBS0Eao4oD1A-Mz1dt34v5mufDv8lHaCtcfovPOka9-q2BE--wa30aJfUJ3C2X-w
link.rule.ids 310,311,783,787,792,793,799,27937,55086
linkProvider IEEE
linkToHtml http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwjV1LT8MwDI7GOMAJ0IZ4kwNHuqVNmjQSFwRMA7aJQxG7TU3jSAjUTbQ9wK8nSccQiAOnRFakxLItW_FnG6EzxVlGpKFBCDENGJA4UFxAQKQKjcgoTzyIZjzhw0d2N42nLXS-qoUBAA8-g57b-ly-nue1-yrrW91inIo1tG7j6oQ31VrLVGVIZH90mT45tJYVf3Pyx8gU7zEGW2j8dVcDFHnp1ZXq5R-_2jD-9zHbqPtdm4cfVl5nB7Wg6KCLa3DJAEvArooKl-9FtiihxCarX6sSPxfYqUjTLQK7HpZ-8QjwsovSwU16NQyWcxGCZ0mqQIDlUBgiZM7AGqgmxEQKOMlttKyZtkYsBSHAKLdEoo1RWsWJYiZKEm1NeBe1i3kBewhHhALXKuE6E8wGRoqGKpcx0AhEnstsH3Uc47NF0_lituT54G_yKdoYpuPRbHQ7uT9Em04QDVrrCLWrtxqOrfuu1ImX2if-hJtG
openUrl ctx_ver=Z39.88-2004&ctx_enc=info%3Aofi%2Fenc%3AUTF-8&rfr_id=info%3Asid%2Fsummon.serialssolutions.com&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Abook&rft.genre=proceeding&rft.title=2019+IEEE+Latin+American+Test+Symposium+%28LATS%29&rft.atitle=Detecting+hard+synapses+faults+in+artificial+neural+networks&rft.au=Krcma%2C+Martin&rft.au=Kotasek%2C+Zdenek&rft.au=Lojda%2C+Jakub&rft.date=2019-03-01&rft.pub=IEEE&rft.spage=1&rft.epage=6&rft_id=info:doi/10.1109%2FLATW.2019.8704637&rft.externalDocID=8704637