Assessment and Improvement of the Pattern Recognition Performance of Memdiode-Based Cross-Point Arrays with Randomly Distributed Stuck-at-Faults

Autores
Aguirre, Fernando Leonel; Pazos, Sebastián Matías; Palumbo, Félix Roberto Mario; Morell, Antoni; Suñé, Jordi; Miranda, Enrique
Año de publicación
2021
Idioma
inglés
Tipo de recurso
artículo
Estado
versión publicada
Descripción
In this work, the effect of randomly distributed stuck-at faults (SAFs) in memristive crosspoint array (CPA)-based single and multi-layer perceptrons (SLPs and MLPs, respectively) intended for pattern recognition tasks is investigated by means of realistic SPICE simulations. The quasi-static memdiode model (QMM) is considered here for the modelling of the synaptic weights implemented with memristors. Following the standard memristive approach, the QMM comprises two coupled equations, one for the electron transport based on the double-diode equation with a single series resistance and a second equation for the internal memory state of the device based on the so-called logistic hysteron. By modifying the state parameter in the current-voltage characteristic, SAFs of different severeness are simulated and the final outcome is analysed. Supervised ex-situ training and two well-known image datasets involving hand-written digits and human faces are employed to assess the inference accuracy of the SLP as a function of the faulty device ratio. The roles played by the memristor’s electrical parameters, line resistance, mapping strategy, image pixelation, and fault type (stuck-at-ON or stuck-at-OFF) on the CPA performance are statistically analysed following a Monte-Carlo approach. Three different re-mapping schemes to help mitigate the effect of the SAFs in the SLP inference phase are thoroughly investigated.In this work, the effect of randomly distributed stuck-at faults (SAFs) in memristive cross-point array (CPA)-based single and multi-layer perceptrons (SLPs and MLPs, respectively) intended for pattern recognition tasks is investigated by means of realistic SPICE simulations. The quasi-static memdiode model (QMM) is considered here for the modelling of the synaptic weights implemented with memristors. Following the standard memristive approach, the QMM comprises two coupled equations, one for the electron transport based on the double-diode equation with a single series resistance and a second equation for the internal memory state of the device based on the so-called logistic hysteron. By modifying the state parameter in the current-voltage characteristic, SAFs of different severeness are simulated and the final outcome is analysed. Supervised ex-situ training and two well-known image datasets involving hand-written digits and human faces are employed to assess the inference accuracy of the SLP as a function of the faulty device ratio. The roles played by the memristor?s electrical parameters, line resistance, mapping strategy, image pixelation, and fault type (stuck-at-ON or stuck-at-OFF) on the CPA performance are statistically analysed following a Monte-Carlo approach. Three different re-mapping schemes to help mitigate the effect of the SAFs in the SLP inference phase are thoroughly investigated.
Fil: Aguirre, Fernando Leonel. Universidad Tecnológica Nacional. Facultad Regional Buenos Aires. Unidad de Investigación y Desarrollo de las Ingenierías; Argentina. Universitat Autònoma de Barcelona; España. Consejo Nacional de Investigaciones Científicas y Técnicas; Argentina
Fil: Pazos, Sebastián Matías. Universidad Tecnológica Nacional. Facultad Regional Buenos Aires. Unidad de Investigación y Desarrollo de las Ingenierías; Argentina. Consejo Nacional de Investigaciones Científicas y Técnicas; Argentina
Fil: Palumbo, Félix Roberto Mario. Universidad Tecnológica Nacional. Facultad Regional Buenos Aires. Unidad de Investigación y Desarrollo de las Ingenierías; Argentina. Consejo Nacional de Investigaciones Científicas y Técnicas; Argentina
Fil: Morell, Antoni. Universitat Autònoma de Barcelona; España
Fil: Suñé, Jordi. Universitat Autònoma de Barcelona; España
Fil: Miranda, Enrique. Universitat Autònoma de Barcelona; España
Materia
STUCK-AT-FAULT
RRAM
PATTERN RECOGNITION
MEMRISTOR
QMM
NEURAL NETWORK
NEUROMORPHICS
Nivel de accesibilidad
acceso abierto
Condiciones de uso
https://creativecommons.org/licenses/by/2.5/ar/
Repositorio
CONICET Digital (CONICET)
Institución
Consejo Nacional de Investigaciones Científicas y Técnicas
OAI Identificador
oai:ri.conicet.gov.ar:11336/155193
Acceder
id CONICETDig_9e05b09e5b327641a029ac4cb8b947eb
oai_identifier_str oai:ri.conicet.gov.ar:11336/155193
network_acronym_str CONICETDig
repository_id_str 3498
network_name_str CONICET Digital (CONICET)
spelling Assessment and Improvement of the Pattern Recognition Performance of Memdiode-Based Cross-Point Arrays with Randomly Distributed Stuck-at-FaultsAguirre, Fernando LeonelPazos, Sebastián MatíasPalumbo, Félix Roberto MarioMorell, AntoniSuñé, JordiMiranda, EnriqueSTUCK-AT-FAULTRRAMPATTERN RECOGNITIONMEMRISTORQMMNEURAL NETWORKNEUROMORPHICShttps://purl.org/becyt/ford/2.10https://purl.org/becyt/ford/2https://purl.org/becyt/ford/2.2https://purl.org/becyt/ford/2In this work, the effect of randomly distributed stuck-at faults (SAFs) in memristive crosspoint array (CPA)-based single and multi-layer perceptrons (SLPs and MLPs, respectively) intended for pattern recognition tasks is investigated by means of realistic SPICE simulations. The quasi-static memdiode model (QMM) is considered here for the modelling of the synaptic weights implemented with memristors. Following the standard memristive approach, the QMM comprises two coupled equations, one for the electron transport based on the double-diode equation with a single series resistance and a second equation for the internal memory state of the device based on the so-called logistic hysteron. By modifying the state parameter in the current-voltage characteristic, SAFs of different severeness are simulated and the final outcome is analysed. Supervised ex-situ training and two well-known image datasets involving hand-written digits and human faces are employed to assess the inference accuracy of the SLP as a function of the faulty device ratio. The roles played by the memristor’s electrical parameters, line resistance, mapping strategy, image pixelation, and fault type (stuck-at-ON or stuck-at-OFF) on the CPA performance are statistically analysed following a Monte-Carlo approach. Three different re-mapping schemes to help mitigate the effect of the SAFs in the SLP inference phase are thoroughly investigated.In this work, the effect of randomly distributed stuck-at faults (SAFs) in memristive cross-point array (CPA)-based single and multi-layer perceptrons (SLPs and MLPs, respectively) intended for pattern recognition tasks is investigated by means of realistic SPICE simulations. The quasi-static memdiode model (QMM) is considered here for the modelling of the synaptic weights implemented with memristors. Following the standard memristive approach, the QMM comprises two coupled equations, one for the electron transport based on the double-diode equation with a single series resistance and a second equation for the internal memory state of the device based on the so-called logistic hysteron. By modifying the state parameter in the current-voltage characteristic, SAFs of different severeness are simulated and the final outcome is analysed. Supervised ex-situ training and two well-known image datasets involving hand-written digits and human faces are employed to assess the inference accuracy of the SLP as a function of the faulty device ratio. The roles played by the memristor?s electrical parameters, line resistance, mapping strategy, image pixelation, and fault type (stuck-at-ON or stuck-at-OFF) on the CPA performance are statistically analysed following a Monte-Carlo approach. Three different re-mapping schemes to help mitigate the effect of the SAFs in the SLP inference phase are thoroughly investigated.Fil: Aguirre, Fernando Leonel. Universidad Tecnológica Nacional. Facultad Regional Buenos Aires. Unidad de Investigación y Desarrollo de las Ingenierías; Argentina. Universitat Autònoma de Barcelona; España. Consejo Nacional de Investigaciones Científicas y Técnicas; ArgentinaFil: Pazos, Sebastián Matías. Universidad Tecnológica Nacional. Facultad Regional Buenos Aires. Unidad de Investigación y Desarrollo de las Ingenierías; Argentina. Consejo Nacional de Investigaciones Científicas y Técnicas; ArgentinaFil: Palumbo, Félix Roberto Mario. Universidad Tecnológica Nacional. Facultad Regional Buenos Aires. Unidad de Investigación y Desarrollo de las Ingenierías; Argentina. Consejo Nacional de Investigaciones Científicas y Técnicas; ArgentinaFil: Morell, Antoni. Universitat Autònoma de Barcelona; EspañaFil: Suñé, Jordi. Universitat Autònoma de Barcelona; EspañaFil: Miranda, Enrique. Universitat Autònoma de Barcelona; EspañaMDPI2021-10-06info:eu-repo/semantics/articleinfo:eu-repo/semantics/publishedVersionhttp://purl.org/coar/resource_type/c_6501info:ar-repo/semantics/articuloapplication/pdfapplication/pdfhttp://hdl.handle.net/11336/155193Aguirre, Fernando Leonel; Pazos, Sebastián Matías; Palumbo, Félix Roberto Mario; Morell, Antoni; Suñé, Jordi; et al.; Assessment and Improvement of the Pattern Recognition Performance of Memdiode-Based Cross-Point Arrays with Randomly Distributed Stuck-at-Faults; MDPI; Electronics; 10; 19; 6-10-2021; 1-242079-92922079-9292CONICET DigitalCONICETenginfo:eu-repo/semantics/altIdentifier/url/https://www.mdpi.com/2079-9292/10/19/2427info:eu-repo/semantics/altIdentifier/doi/10.3390/electronics10192427info:eu-repo/semantics/openAccesshttps://creativecommons.org/licenses/by/2.5/ar/reponame:CONICET Digital (CONICET)instname:Consejo Nacional de Investigaciones Científicas y Técnicas2025-11-05T10:00:58Zoai:ri.conicet.gov.ar:11336/155193instacron:CONICETInstitucionalhttp://ri.conicet.gov.ar/Organismo científico-tecnológicoNo correspondehttp://ri.conicet.gov.ar/oai/requestdasensio@conicet.gov.ar; lcarlino@conicet.gov.arArgentinaNo correspondeNo correspondeNo correspondeopendoar:34982025-11-05 10:00:59.114CONICET Digital (CONICET) - Consejo Nacional de Investigaciones Científicas y Técnicasfalse
dc.title.none.fl_str_mv Assessment and Improvement of the Pattern Recognition Performance of Memdiode-Based Cross-Point Arrays with Randomly Distributed Stuck-at-Faults
title Assessment and Improvement of the Pattern Recognition Performance of Memdiode-Based Cross-Point Arrays with Randomly Distributed Stuck-at-Faults
spellingShingle Assessment and Improvement of the Pattern Recognition Performance of Memdiode-Based Cross-Point Arrays with Randomly Distributed Stuck-at-Faults
Aguirre, Fernando Leonel
STUCK-AT-FAULT
RRAM
PATTERN RECOGNITION
MEMRISTOR
QMM
NEURAL NETWORK
NEUROMORPHICS
title_short Assessment and Improvement of the Pattern Recognition Performance of Memdiode-Based Cross-Point Arrays with Randomly Distributed Stuck-at-Faults
title_full Assessment and Improvement of the Pattern Recognition Performance of Memdiode-Based Cross-Point Arrays with Randomly Distributed Stuck-at-Faults
title_fullStr Assessment and Improvement of the Pattern Recognition Performance of Memdiode-Based Cross-Point Arrays with Randomly Distributed Stuck-at-Faults
title_full_unstemmed Assessment and Improvement of the Pattern Recognition Performance of Memdiode-Based Cross-Point Arrays with Randomly Distributed Stuck-at-Faults
title_sort Assessment and Improvement of the Pattern Recognition Performance of Memdiode-Based Cross-Point Arrays with Randomly Distributed Stuck-at-Faults
dc.creator.none.fl_str_mv Aguirre, Fernando Leonel
Pazos, Sebastián Matías
Palumbo, Félix Roberto Mario
Morell, Antoni
Suñé, Jordi
Miranda, Enrique
author Aguirre, Fernando Leonel
author_facet Aguirre, Fernando Leonel
Pazos, Sebastián Matías
Palumbo, Félix Roberto Mario
Morell, Antoni
Suñé, Jordi
Miranda, Enrique
author_role author
author2 Pazos, Sebastián Matías
Palumbo, Félix Roberto Mario
Morell, Antoni
Suñé, Jordi
Miranda, Enrique
author2_role author
author
author
author
author
dc.subject.none.fl_str_mv STUCK-AT-FAULT
RRAM
PATTERN RECOGNITION
MEMRISTOR
QMM
NEURAL NETWORK
NEUROMORPHICS
topic STUCK-AT-FAULT
RRAM
PATTERN RECOGNITION
MEMRISTOR
QMM
NEURAL NETWORK
NEUROMORPHICS
purl_subject.fl_str_mv https://purl.org/becyt/ford/2.10
https://purl.org/becyt/ford/2
https://purl.org/becyt/ford/2.2
https://purl.org/becyt/ford/2
dc.description.none.fl_txt_mv In this work, the effect of randomly distributed stuck-at faults (SAFs) in memristive crosspoint array (CPA)-based single and multi-layer perceptrons (SLPs and MLPs, respectively) intended for pattern recognition tasks is investigated by means of realistic SPICE simulations. The quasi-static memdiode model (QMM) is considered here for the modelling of the synaptic weights implemented with memristors. Following the standard memristive approach, the QMM comprises two coupled equations, one for the electron transport based on the double-diode equation with a single series resistance and a second equation for the internal memory state of the device based on the so-called logistic hysteron. By modifying the state parameter in the current-voltage characteristic, SAFs of different severeness are simulated and the final outcome is analysed. Supervised ex-situ training and two well-known image datasets involving hand-written digits and human faces are employed to assess the inference accuracy of the SLP as a function of the faulty device ratio. The roles played by the memristor’s electrical parameters, line resistance, mapping strategy, image pixelation, and fault type (stuck-at-ON or stuck-at-OFF) on the CPA performance are statistically analysed following a Monte-Carlo approach. Three different re-mapping schemes to help mitigate the effect of the SAFs in the SLP inference phase are thoroughly investigated.In this work, the effect of randomly distributed stuck-at faults (SAFs) in memristive cross-point array (CPA)-based single and multi-layer perceptrons (SLPs and MLPs, respectively) intended for pattern recognition tasks is investigated by means of realistic SPICE simulations. The quasi-static memdiode model (QMM) is considered here for the modelling of the synaptic weights implemented with memristors. Following the standard memristive approach, the QMM comprises two coupled equations, one for the electron transport based on the double-diode equation with a single series resistance and a second equation for the internal memory state of the device based on the so-called logistic hysteron. By modifying the state parameter in the current-voltage characteristic, SAFs of different severeness are simulated and the final outcome is analysed. Supervised ex-situ training and two well-known image datasets involving hand-written digits and human faces are employed to assess the inference accuracy of the SLP as a function of the faulty device ratio. The roles played by the memristor?s electrical parameters, line resistance, mapping strategy, image pixelation, and fault type (stuck-at-ON or stuck-at-OFF) on the CPA performance are statistically analysed following a Monte-Carlo approach. Three different re-mapping schemes to help mitigate the effect of the SAFs in the SLP inference phase are thoroughly investigated.
Fil: Aguirre, Fernando Leonel. Universidad Tecnológica Nacional. Facultad Regional Buenos Aires. Unidad de Investigación y Desarrollo de las Ingenierías; Argentina. Universitat Autònoma de Barcelona; España. Consejo Nacional de Investigaciones Científicas y Técnicas; Argentina
Fil: Pazos, Sebastián Matías. Universidad Tecnológica Nacional. Facultad Regional Buenos Aires. Unidad de Investigación y Desarrollo de las Ingenierías; Argentina. Consejo Nacional de Investigaciones Científicas y Técnicas; Argentina
Fil: Palumbo, Félix Roberto Mario. Universidad Tecnológica Nacional. Facultad Regional Buenos Aires. Unidad de Investigación y Desarrollo de las Ingenierías; Argentina. Consejo Nacional de Investigaciones Científicas y Técnicas; Argentina
Fil: Morell, Antoni. Universitat Autònoma de Barcelona; España
Fil: Suñé, Jordi. Universitat Autònoma de Barcelona; España
Fil: Miranda, Enrique. Universitat Autònoma de Barcelona; España
description In this work, the effect of randomly distributed stuck-at faults (SAFs) in memristive crosspoint array (CPA)-based single and multi-layer perceptrons (SLPs and MLPs, respectively) intended for pattern recognition tasks is investigated by means of realistic SPICE simulations. The quasi-static memdiode model (QMM) is considered here for the modelling of the synaptic weights implemented with memristors. Following the standard memristive approach, the QMM comprises two coupled equations, one for the electron transport based on the double-diode equation with a single series resistance and a second equation for the internal memory state of the device based on the so-called logistic hysteron. By modifying the state parameter in the current-voltage characteristic, SAFs of different severeness are simulated and the final outcome is analysed. Supervised ex-situ training and two well-known image datasets involving hand-written digits and human faces are employed to assess the inference accuracy of the SLP as a function of the faulty device ratio. The roles played by the memristor’s electrical parameters, line resistance, mapping strategy, image pixelation, and fault type (stuck-at-ON or stuck-at-OFF) on the CPA performance are statistically analysed following a Monte-Carlo approach. Three different re-mapping schemes to help mitigate the effect of the SAFs in the SLP inference phase are thoroughly investigated.In this work, the effect of randomly distributed stuck-at faults (SAFs) in memristive cross-point array (CPA)-based single and multi-layer perceptrons (SLPs and MLPs, respectively) intended for pattern recognition tasks is investigated by means of realistic SPICE simulations. The quasi-static memdiode model (QMM) is considered here for the modelling of the synaptic weights implemented with memristors. Following the standard memristive approach, the QMM comprises two coupled equations, one for the electron transport based on the double-diode equation with a single series resistance and a second equation for the internal memory state of the device based on the so-called logistic hysteron. By modifying the state parameter in the current-voltage characteristic, SAFs of different severeness are simulated and the final outcome is analysed. Supervised ex-situ training and two well-known image datasets involving hand-written digits and human faces are employed to assess the inference accuracy of the SLP as a function of the faulty device ratio. The roles played by the memristor?s electrical parameters, line resistance, mapping strategy, image pixelation, and fault type (stuck-at-ON or stuck-at-OFF) on the CPA performance are statistically analysed following a Monte-Carlo approach. Three different re-mapping schemes to help mitigate the effect of the SAFs in the SLP inference phase are thoroughly investigated.
publishDate 2021
dc.date.none.fl_str_mv 2021-10-06
dc.type.none.fl_str_mv info:eu-repo/semantics/article
info:eu-repo/semantics/publishedVersion
http://purl.org/coar/resource_type/c_6501
info:ar-repo/semantics/articulo
format article
status_str publishedVersion
dc.identifier.none.fl_str_mv http://hdl.handle.net/11336/155193
Aguirre, Fernando Leonel; Pazos, Sebastián Matías; Palumbo, Félix Roberto Mario; Morell, Antoni; Suñé, Jordi; et al.; Assessment and Improvement of the Pattern Recognition Performance of Memdiode-Based Cross-Point Arrays with Randomly Distributed Stuck-at-Faults; MDPI; Electronics; 10; 19; 6-10-2021; 1-24
2079-9292
2079-9292
CONICET Digital
CONICET
url http://hdl.handle.net/11336/155193
identifier_str_mv Aguirre, Fernando Leonel; Pazos, Sebastián Matías; Palumbo, Félix Roberto Mario; Morell, Antoni; Suñé, Jordi; et al.; Assessment and Improvement of the Pattern Recognition Performance of Memdiode-Based Cross-Point Arrays with Randomly Distributed Stuck-at-Faults; MDPI; Electronics; 10; 19; 6-10-2021; 1-24
2079-9292
CONICET Digital
CONICET
dc.language.none.fl_str_mv eng
language eng
dc.relation.none.fl_str_mv info:eu-repo/semantics/altIdentifier/url/https://www.mdpi.com/2079-9292/10/19/2427
info:eu-repo/semantics/altIdentifier/doi/10.3390/electronics10192427
dc.rights.none.fl_str_mv info:eu-repo/semantics/openAccess
https://creativecommons.org/licenses/by/2.5/ar/
eu_rights_str_mv openAccess
rights_invalid_str_mv https://creativecommons.org/licenses/by/2.5/ar/
dc.format.none.fl_str_mv application/pdf
application/pdf
dc.publisher.none.fl_str_mv MDPI
publisher.none.fl_str_mv MDPI
dc.source.none.fl_str_mv reponame:CONICET Digital (CONICET)
instname:Consejo Nacional de Investigaciones Científicas y Técnicas
reponame_str CONICET Digital (CONICET)
collection CONICET Digital (CONICET)
instname_str Consejo Nacional de Investigaciones Científicas y Técnicas
repository.name.fl_str_mv CONICET Digital (CONICET) - Consejo Nacional de Investigaciones Científicas y Técnicas
repository.mail.fl_str_mv dasensio@conicet.gov.ar; lcarlino@conicet.gov.ar
_version_ 1847977449752625152
score 13.087074

Publicaciones similares