Oscillatory Neural Networks Using VO2 Based Phase Encoded Logic

Nano-oscillators based on phase-transition materials are being explored for the implementation of different non-conventional computing paradigms. In particular, vanadium dioxide (VO2) devices are used to design autonomous non-linear oscillators from which oscillatory neural networks (ONNs) can be de...

ver descrição completa

Detalhes bibliográficos
Autores: Núñez Martínez, Juan, Avedillo de Juan, María José, Jiménez, Manuel, Quintana Toledo, José María, Todri Sanial, Aida, Corti, Elisabetta, Karg, Siegfried, Linares Barranco, Bernabé
Tipo de documento: artigo
Estado:Versão publicada
Data de publicação:2021
País:España
Recursos:Universidad de Sevilla (US)
Repositório:idUS. Depósito de Investigación de la Universidad de Sevilla
OAI Identifier:oai:idus.us.es:11441/135098
Acesso em linha:https://hdl.handle.net/11441/135098
https://doi.org/10.3389/fnins.2021.655823
Access Level:Acceso aberto
Palavra-chave:Phase transition materials
VO2
Nano-oscillators
ONNs
Neuromorphics
id ES_ef25e99a16aa874464b5fb17cdb1ea23
oai_identifier_str oai:idus.us.es:11441/135098
network_acronym_str ES
network_name_str España
repository_id_str
spelling Oscillatory Neural Networks Using VO2 Based Phase Encoded LogicNúñez Martínez, JuanAvedillo de Juan, María JoséJiménez, ManuelQuintana Toledo, José MaríaTodri Sanial, AidaCorti, ElisabettaKarg, SiegfriedLinares Barranco, BernabéPhase transition materialsVO2Nano-oscillatorsONNsNeuromorphicsNano-oscillators based on phase-transition materials are being explored for the implementation of different non-conventional computing paradigms. In particular, vanadium dioxide (VO2) devices are used to design autonomous non-linear oscillators from which oscillatory neural networks (ONNs) can be developed. In this work, we propose a new architecture for ONNs in which sub-harmonic injection locking (SHIL) is exploited to ensure that the phase information encoded in each neuron can only take two values. In this sense, the implementation of ONNs from neurons that inherently encode information with two-phase values has advantages in terms of robustness and tolerance to variability present in VO2 devices. Unlike conventional interconnection schemes, in which the sign of the weights is coded in the value of the resistances, in our proposal the negative (positive) weights are coded using static inverting (non-inverting) logic at the output of the oscillator. The operation of the proposed architecture is shown for pattern recognition applications.Horizon 2020 – 871501Ministerio de Economía y Competitividad FEDER TEC2017-87052-PFrontiers MediaElectrónica y ElectromagnetismoEuropean Union (UE). H2020European Commission (EC). Fondo Europeo de Desarrollo Regional (FEDER)Ministerio de Economía y Competitividad (MINECO). España2021info:eu-repo/semantics/articleinfo:eu-repo/semantics/publishedVersionapplication/pdfapplication/pdfhttps://hdl.handle.net/11441/135098https://doi.org/10.3389/fnins.2021.655823reponame:idUS. Depósito de Investigación de la Universidad de Sevillainstname:Universidad de Sevilla (US)InglésFrontiers in Neuroscience, 15, 655823.871501TEC2017-87052-Phttps://dx.doi.org/10.3389/fnins.2021.655823info:eu-repo/semantics/openAccessoai:idus.us.es:11441/1350982026-06-17T12:51:07Z
dc.title.none.fl_str_mv Oscillatory Neural Networks Using VO2 Based Phase Encoded Logic
title Oscillatory Neural Networks Using VO2 Based Phase Encoded Logic
spellingShingle Oscillatory Neural Networks Using VO2 Based Phase Encoded Logic
Núñez Martínez, Juan
Phase transition materials
VO2
Nano-oscillators
ONNs
Neuromorphics
title_short Oscillatory Neural Networks Using VO2 Based Phase Encoded Logic
title_full Oscillatory Neural Networks Using VO2 Based Phase Encoded Logic
title_fullStr Oscillatory Neural Networks Using VO2 Based Phase Encoded Logic
title_full_unstemmed Oscillatory Neural Networks Using VO2 Based Phase Encoded Logic
title_sort Oscillatory Neural Networks Using VO2 Based Phase Encoded Logic
dc.creator.none.fl_str_mv Núñez Martínez, Juan
Avedillo de Juan, María José
Jiménez, Manuel
Quintana Toledo, José María
Todri Sanial, Aida
Corti, Elisabetta
Karg, Siegfried
Linares Barranco, Bernabé
author Núñez Martínez, Juan
author_facet Núñez Martínez, Juan
Avedillo de Juan, María José
Jiménez, Manuel
Quintana Toledo, José María
Todri Sanial, Aida
Corti, Elisabetta
Karg, Siegfried
Linares Barranco, Bernabé
author_role author
author2 Avedillo de Juan, María José
Jiménez, Manuel
Quintana Toledo, José María
Todri Sanial, Aida
Corti, Elisabetta
Karg, Siegfried
Linares Barranco, Bernabé
author2_role author
author
author
author
author
author
author
dc.contributor.none.fl_str_mv Electrónica y Electromagnetismo
European Union (UE). H2020
European Commission (EC). Fondo Europeo de Desarrollo Regional (FEDER)
Ministerio de Economía y Competitividad (MINECO). España
dc.subject.none.fl_str_mv Phase transition materials
VO2
Nano-oscillators
ONNs
Neuromorphics
topic Phase transition materials
VO2
Nano-oscillators
ONNs
Neuromorphics
description Nano-oscillators based on phase-transition materials are being explored for the implementation of different non-conventional computing paradigms. In particular, vanadium dioxide (VO2) devices are used to design autonomous non-linear oscillators from which oscillatory neural networks (ONNs) can be developed. In this work, we propose a new architecture for ONNs in which sub-harmonic injection locking (SHIL) is exploited to ensure that the phase information encoded in each neuron can only take two values. In this sense, the implementation of ONNs from neurons that inherently encode information with two-phase values has advantages in terms of robustness and tolerance to variability present in VO2 devices. Unlike conventional interconnection schemes, in which the sign of the weights is coded in the value of the resistances, in our proposal the negative (positive) weights are coded using static inverting (non-inverting) logic at the output of the oscillator. The operation of the proposed architecture is shown for pattern recognition applications.
publishDate 2021
dc.date.none.fl_str_mv 2021
dc.type.none.fl_str_mv info:eu-repo/semantics/article
info:eu-repo/semantics/publishedVersion
format article
status_str publishedVersion
dc.identifier.none.fl_str_mv https://hdl.handle.net/11441/135098
https://doi.org/10.3389/fnins.2021.655823
url https://hdl.handle.net/11441/135098
https://doi.org/10.3389/fnins.2021.655823
dc.language.none.fl_str_mv Inglés
language_invalid_str_mv Inglés
dc.relation.none.fl_str_mv Frontiers in Neuroscience, 15, 655823.
871501
TEC2017-87052-P
https://dx.doi.org/10.3389/fnins.2021.655823
dc.rights.none.fl_str_mv info:eu-repo/semantics/openAccess
eu_rights_str_mv openAccess
dc.format.none.fl_str_mv application/pdf
application/pdf
dc.publisher.none.fl_str_mv Frontiers Media
publisher.none.fl_str_mv Frontiers Media
dc.source.none.fl_str_mv reponame:idUS. Depósito de Investigación de la Universidad de Sevilla
instname:Universidad de Sevilla (US)
instname_str Universidad de Sevilla (US)
reponame_str idUS. Depósito de Investigación de la Universidad de Sevilla
collection idUS. Depósito de Investigación de la Universidad de Sevilla
repository.name.fl_str_mv
repository.mail.fl_str_mv
_version_ 1869423836270690304
score 15.301603

Registros relacionados