Learning by mistakes in memristor networks

Autores
Carbajal, Juan Pablo; Mártin, Daniel Alejandro; Chialvo, Dante Renato
Año de publicación
2022
Idioma
inglés
Tipo de recurso
artículo
Estado
versión publicada
Descripción
Recent results revived the interest in the implementation of analog devices able to perform brainlike operations. Here we introduce a training algorithm for a memristor network which is inspired by previous work on biological learning. Robust results are obtained from computer simulations of a network of voltage-controlled memristive devices. Its implementation in hardware is straightforward, being scalable and requiring very little peripheral computation overhead.
Fil: Carbajal, Juan Pablo. University of Applied Sciences of Eastern Switzerland; Suiza
Fil: Mártin, Daniel Alejandro. Consejo Nacional de Investigaciones Científicas y Técnicas. Instituto de Ciencias Físicas. - Universidad Nacional de San Martín. Instituto de Ciencias Físicas; Argentina
Fil: Chialvo, Dante Renato. Consejo Nacional de Investigaciones Científicas y Técnicas. Instituto de Ciencias Físicas. - Universidad Nacional de San Martín. Instituto de Ciencias Físicas; Argentina
Materia
MEMRISTOR
NETWORKS
NEUROMORPHING
NEURAL NETWORKS
Nivel de accesibilidad
acceso abierto
Condiciones de uso
https://creativecommons.org/licenses/by-nc-sa/2.5/ar/
Repositorio
CONICET Digital (CONICET)
Institución
Consejo Nacional de Investigaciones Científicas y Técnicas
OAI Identificador
oai:ri.conicet.gov.ar:11336/213954
Acceder
id CONICETDig_d03bc4d4813253f9fe452bc7e0ef5584
oai_identifier_str oai:ri.conicet.gov.ar:11336/213954
network_acronym_str CONICETDig
repository_id_str 3498
network_name_str CONICET Digital (CONICET)
spelling Learning by mistakes in memristor networksCarbajal, Juan PabloMártin, Daniel AlejandroChialvo, Dante RenatoMEMRISTORNETWORKSNEUROMORPHINGNEURAL NETWORKShttps://purl.org/becyt/ford/1.3https://purl.org/becyt/ford/1Recent results revived the interest in the implementation of analog devices able to perform brainlike operations. Here we introduce a training algorithm for a memristor network which is inspired by previous work on biological learning. Robust results are obtained from computer simulations of a network of voltage-controlled memristive devices. Its implementation in hardware is straightforward, being scalable and requiring very little peripheral computation overhead.Fil: Carbajal, Juan Pablo. University of Applied Sciences of Eastern Switzerland; SuizaFil: Mártin, Daniel Alejandro. Consejo Nacional de Investigaciones Científicas y Técnicas. Instituto de Ciencias Físicas. - Universidad Nacional de San Martín. Instituto de Ciencias Físicas; ArgentinaFil: Chialvo, Dante Renato. Consejo Nacional de Investigaciones Científicas y Técnicas. Instituto de Ciencias Físicas. - Universidad Nacional de San Martín. Instituto de Ciencias Físicas; ArgentinaAmerican Physical Society2022-05info:eu-repo/semantics/articleinfo:eu-repo/semantics/publishedVersionhttp://purl.org/coar/resource_type/c_6501info:ar-repo/semantics/articuloapplication/pdfapplication/pdfapplication/pdfhttp://hdl.handle.net/11336/213954Carbajal, Juan Pablo; Mártin, Daniel Alejandro; Chialvo, Dante Renato; Learning by mistakes in memristor networks; American Physical Society; Physical Review E: Statistical, Nonlinear and Soft Matter Physics; 105; 5; 5-2022; 1-101539-37552470-0053CONICET DigitalCONICETenginfo:eu-repo/semantics/altIdentifier/url/https://journals.aps.org/pre/abstract/10.1103/PhysRevE.105.054306info:eu-repo/semantics/altIdentifier/doi/10.1103/PhysRevE.105.054306info:eu-repo/semantics/openAccesshttps://creativecommons.org/licenses/by-nc-sa/2.5/ar/reponame:CONICET Digital (CONICET)instname:Consejo Nacional de Investigaciones Científicas y Técnicas2025-10-15T14:21:29Zoai:ri.conicet.gov.ar:11336/213954instacron: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:34982025-10-15 14:21:29.314CONICET Digital (CONICET) - Consejo Nacional de Investigaciones Científicas y Técnicasfalse
dc.title.none.fl_str_mv Learning by mistakes in memristor networks
title Learning by mistakes in memristor networks
spellingShingle Learning by mistakes in memristor networks
Carbajal, Juan Pablo
MEMRISTOR
NETWORKS
NEUROMORPHING
NEURAL NETWORKS
title_short Learning by mistakes in memristor networks
title_full Learning by mistakes in memristor networks
title_fullStr Learning by mistakes in memristor networks
title_full_unstemmed Learning by mistakes in memristor networks
title_sort Learning by mistakes in memristor networks
dc.creator.none.fl_str_mv Carbajal, Juan Pablo
Mártin, Daniel Alejandro
Chialvo, Dante Renato
author Carbajal, Juan Pablo
author_facet Carbajal, Juan Pablo
Mártin, Daniel Alejandro
Chialvo, Dante Renato
author_role author
author2 Mártin, Daniel Alejandro
Chialvo, Dante Renato
author2_role author
author
dc.subject.none.fl_str_mv MEMRISTOR
NETWORKS
NEUROMORPHING
NEURAL NETWORKS
topic MEMRISTOR
NETWORKS
NEUROMORPHING
NEURAL NETWORKS
purl_subject.fl_str_mv https://purl.org/becyt/ford/1.3
https://purl.org/becyt/ford/1
dc.description.none.fl_txt_mv Recent results revived the interest in the implementation of analog devices able to perform brainlike operations. Here we introduce a training algorithm for a memristor network which is inspired by previous work on biological learning. Robust results are obtained from computer simulations of a network of voltage-controlled memristive devices. Its implementation in hardware is straightforward, being scalable and requiring very little peripheral computation overhead.
Fil: Carbajal, Juan Pablo. University of Applied Sciences of Eastern Switzerland; Suiza
Fil: Mártin, Daniel Alejandro. Consejo Nacional de Investigaciones Científicas y Técnicas. Instituto de Ciencias Físicas. - Universidad Nacional de San Martín. Instituto de Ciencias Físicas; Argentina
Fil: Chialvo, Dante Renato. Consejo Nacional de Investigaciones Científicas y Técnicas. Instituto de Ciencias Físicas. - Universidad Nacional de San Martín. Instituto de Ciencias Físicas; Argentina
description Recent results revived the interest in the implementation of analog devices able to perform brainlike operations. Here we introduce a training algorithm for a memristor network which is inspired by previous work on biological learning. Robust results are obtained from computer simulations of a network of voltage-controlled memristive devices. Its implementation in hardware is straightforward, being scalable and requiring very little peripheral computation overhead.
publishDate 2022
dc.date.none.fl_str_mv 2022-05
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/11336/213954
Carbajal, Juan Pablo; Mártin, Daniel Alejandro; Chialvo, Dante Renato; Learning by mistakes in memristor networks; American Physical Society; Physical Review E: Statistical, Nonlinear and Soft Matter Physics; 105; 5; 5-2022; 1-10
1539-3755
2470-0053
CONICET Digital
CONICET
url http://hdl.handle.net/11336/213954
identifier_str_mv Carbajal, Juan Pablo; Mártin, Daniel Alejandro; Chialvo, Dante Renato; Learning by mistakes in memristor networks; American Physical Society; Physical Review E: Statistical, Nonlinear and Soft Matter Physics; 105; 5; 5-2022; 1-10
1539-3755
2470-0053
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://journals.aps.org/pre/abstract/10.1103/PhysRevE.105.054306
info:eu-repo/semantics/altIdentifier/doi/10.1103/PhysRevE.105.054306
dc.rights.none.fl_str_mv info:eu-repo/semantics/openAccess
https://creativecommons.org/licenses/by-nc-sa/2.5/ar/
eu_rights_str_mv openAccess
rights_invalid_str_mv https://creativecommons.org/licenses/by-nc-sa/2.5/ar/
dc.format.none.fl_str_mv application/pdf
application/pdf
application/pdf
dc.publisher.none.fl_str_mv American Physical Society
publisher.none.fl_str_mv American Physical Society
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_ 1846082603486019584
score 13.22299

Publicaciones similares