Toward Reflective Spiking Neural Networks Exploiting Memristive Devices

The design of modern convolutional artificial neural networks (ANNs) composed of formal neurons copies the architecture of the visual cortex. Signals proceed through a hierarchy, where receptive fields become increasingly more complex and coding sparse. Nowadays, ANNs outperform humans in controlled...

ver descrição completa

Detalhes bibliográficos
Autores: Makarov Slizneva, Valeriy, Lobov, Sergey A., Shchanikov, Sergey, Mikhaylov, Alexey, Kazantsev, Viktor B.
Tipo de documento: artigo
Data de publicação:2022
País:España
Recursos:Universidad Complutense de Madrid (UCM)
Repositório:Docta Complutense
Idioma:inglês
OAI Identifier:oai:docta.ucm.es:20.500.14352/71954
Acesso em linha:https://hdl.handle.net/20.500.14352/71954
Access Level:Acceso aberto
Palavra-chave:004.032.26
Spiking neural networks (SNNs): Memristors and memristive systems
High-dimensional brain
Plasticity
Reflective systems
Investigación operativa (Matemáticas)
Neurociencias (Medicina)
Biomatemáticas
1207 Investigación Operativa
2490 Neurociencias
2404 Biomatemáticas
id ES_43f9fdb32c824c26e1eb6403e3aac3e6
oai_identifier_str oai:docta.ucm.es:20.500.14352/71954
network_acronym_str ES
network_name_str España
repository_id_str
spelling Toward Reflective Spiking Neural Networks Exploiting Memristive DevicesMakarov Slizneva, ValeriyLobov, Sergey A.Shchanikov, SergeyMikhaylov, AlexeyKazantsev, Viktor B.004.032.26Spiking neural networks (SNNs): Memristors and memristive systemsHigh-dimensional brainPlasticityReflective systemsInvestigación operativa (Matemáticas)Neurociencias (Medicina)Biomatemáticas1207 Investigación Operativa2490 Neurociencias2404 BiomatemáticasThe design of modern convolutional artificial neural networks (ANNs) composed of formal neurons copies the architecture of the visual cortex. Signals proceed through a hierarchy, where receptive fields become increasingly more complex and coding sparse. Nowadays, ANNs outperform humans in controlled pattern recognition tasks yet remain far behind in cognition. In part, it happens due to limited knowledge about the higher echelons of the brain hierarchy, where neurons actively generate predictions about what will happen next, i.e., the information processing jumps from reflex to reflection. In this study, we forecast that spiking neural networks (SNNs) can achieve the next qualitative leap. Reflective SNNs may take advantage of their intrinsic dynamics and mimic complex, not reflex-based, brain actions. They also enable a significant reduction in energy consumption. However, the training of SNNs is a challenging problem, strongly limiting their deployment. We then briefly overview new insights provided by the concept of a high-dimensional brain, which has been put forward to explain the potential power of single neurons in higher brain stations and deep SNN layers. Finally, we discuss the prospect of implementing neural networks in memristive systems. Such systems can densely pack on a chip 2D or 3D arrays of plastic synaptic contacts directly processing analog information. Thus, memristive devices are a good candidate for implementing in-memory and in-sensor computing. Then, memristive SNNs can diverge from the development of ANNs and build their niche, cognitive, or reflective computations.Frontiers MediaUniversidad Complutense de Madrid20222022-06-1620222022-06-16journal articlehttp://purl.org/coar/resource_type/c_6501info:eu-repo/semantics/articleapplication/pdfhttps://hdl.handle.net/20.500.14352/71954reponame:Docta Complutenseinstname:Universidad Complutense de Madrid (UCM)Inglésengopen accesshttp://purl.org/coar/access_right/c_abf2Atribución 3.0 Españahttps://creativecommons.org/licenses/by/3.0/es/info:eu-repo/semantics/openAccessoai:docta.ucm.es:20.500.14352/719542026-06-02T12:44:21Z
dc.title.none.fl_str_mv Toward Reflective Spiking Neural Networks Exploiting Memristive Devices
title Toward Reflective Spiking Neural Networks Exploiting Memristive Devices
spellingShingle Toward Reflective Spiking Neural Networks Exploiting Memristive Devices
Makarov Slizneva, Valeriy
004.032.26
Spiking neural networks (SNNs): Memristors and memristive systems
High-dimensional brain
Plasticity
Reflective systems
Investigación operativa (Matemáticas)
Neurociencias (Medicina)
Biomatemáticas
1207 Investigación Operativa
2490 Neurociencias
2404 Biomatemáticas
title_short Toward Reflective Spiking Neural Networks Exploiting Memristive Devices
title_full Toward Reflective Spiking Neural Networks Exploiting Memristive Devices
title_fullStr Toward Reflective Spiking Neural Networks Exploiting Memristive Devices
title_full_unstemmed Toward Reflective Spiking Neural Networks Exploiting Memristive Devices
title_sort Toward Reflective Spiking Neural Networks Exploiting Memristive Devices
dc.creator.none.fl_str_mv Makarov Slizneva, Valeriy
Lobov, Sergey A.
Shchanikov, Sergey
Mikhaylov, Alexey
Kazantsev, Viktor B.
author Makarov Slizneva, Valeriy
author_facet Makarov Slizneva, Valeriy
Lobov, Sergey A.
Shchanikov, Sergey
Mikhaylov, Alexey
Kazantsev, Viktor B.
author_role author
author2 Lobov, Sergey A.
Shchanikov, Sergey
Mikhaylov, Alexey
Kazantsev, Viktor B.
author2_role author
author
author
author
dc.contributor.none.fl_str_mv Universidad Complutense de Madrid
dc.subject.none.fl_str_mv 004.032.26
Spiking neural networks (SNNs): Memristors and memristive systems
High-dimensional brain
Plasticity
Reflective systems
Investigación operativa (Matemáticas)
Neurociencias (Medicina)
Biomatemáticas
1207 Investigación Operativa
2490 Neurociencias
2404 Biomatemáticas
topic 004.032.26
Spiking neural networks (SNNs): Memristors and memristive systems
High-dimensional brain
Plasticity
Reflective systems
Investigación operativa (Matemáticas)
Neurociencias (Medicina)
Biomatemáticas
1207 Investigación Operativa
2490 Neurociencias
2404 Biomatemáticas
description The design of modern convolutional artificial neural networks (ANNs) composed of formal neurons copies the architecture of the visual cortex. Signals proceed through a hierarchy, where receptive fields become increasingly more complex and coding sparse. Nowadays, ANNs outperform humans in controlled pattern recognition tasks yet remain far behind in cognition. In part, it happens due to limited knowledge about the higher echelons of the brain hierarchy, where neurons actively generate predictions about what will happen next, i.e., the information processing jumps from reflex to reflection. In this study, we forecast that spiking neural networks (SNNs) can achieve the next qualitative leap. Reflective SNNs may take advantage of their intrinsic dynamics and mimic complex, not reflex-based, brain actions. They also enable a significant reduction in energy consumption. However, the training of SNNs is a challenging problem, strongly limiting their deployment. We then briefly overview new insights provided by the concept of a high-dimensional brain, which has been put forward to explain the potential power of single neurons in higher brain stations and deep SNN layers. Finally, we discuss the prospect of implementing neural networks in memristive systems. Such systems can densely pack on a chip 2D or 3D arrays of plastic synaptic contacts directly processing analog information. Thus, memristive devices are a good candidate for implementing in-memory and in-sensor computing. Then, memristive SNNs can diverge from the development of ANNs and build their niche, cognitive, or reflective computations.
publishDate 2022
dc.date.none.fl_str_mv 2022
2022-06-16
2022
2022-06-16
dc.type.none.fl_str_mv journal article
http://purl.org/coar/resource_type/c_6501
dc.type.openaire.fl_str_mv info:eu-repo/semantics/article
format article
dc.identifier.none.fl_str_mv https://hdl.handle.net/20.500.14352/71954
url https://hdl.handle.net/20.500.14352/71954
dc.language.none.fl_str_mv Inglés
eng
language_invalid_str_mv Inglés
language eng
dc.rights.none.fl_str_mv open access
http://purl.org/coar/access_right/c_abf2
Atribución 3.0 España
https://creativecommons.org/licenses/by/3.0/es/
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
Atribución 3.0 España
https://creativecommons.org/licenses/by/3.0/es/
eu_rights_str_mv openAccess
dc.format.none.fl_str_mv application/pdf
dc.publisher.none.fl_str_mv Frontiers Media
publisher.none.fl_str_mv Frontiers Media
dc.source.none.fl_str_mv reponame:Docta Complutense
instname:Universidad Complutense de Madrid (UCM)
instname_str Universidad Complutense de Madrid (UCM)
reponame_str Docta Complutense
collection Docta Complutense
repository.name.fl_str_mv
repository.mail.fl_str_mv
_version_ 1869407061952954368
score 15,301629

Registros relacionados