Blessing of dimensionality in spiking neural networks: the by-chance functional learning

Spiking neural networks (SNNs) have significant potential for a power-efficient neuromorphic AI. However, their training is challenging since most of the learning principles known from artificial neural networks are hardly applicable. Recently, the concept of “blessing of dimensionality” has success...

Full description

Bibliographic Details
Authors: Makarov Slizneva, Valeriy, Lobov, Sergey
Format: article
Publication Date:2025
Country:España
Institution:Universidad Complutense de Madrid (UCM)
Repository:Docta Complutense
Language:English
OAI Identifier:oai:docta.ucm.es:20.500.14352/130210
Online Access:https://hdl.handle.net/20.500.14352/130210
Access Level:Open access
Keyword:Cibernética matemática
1207.03 Cibernética
id ES_fdb13eeeb4dbed114723a35a0b2fc7e2
oai_identifier_str oai:docta.ucm.es:20.500.14352/130210
network_acronym_str ES
network_name_str España
repository_id_str
spelling Blessing of dimensionality in spiking neural networks: the by-chance functional learningMakarov Slizneva, ValeriyLobov, SergeyCibernética matemática1207.03 CibernéticaSpiking neural networks (SNNs) have significant potential for a power-efficient neuromorphic AI. However, their training is challenging since most of the learning principles known from artificial neural networks are hardly applicable. Recently, the concept of “blessing of dimensionality” has successfully been used to treat high-dimensional data and representations of reality. It exploits the fundamental trade-off between the complexity and simplicity of statistical sets in high-dimensional spaces without relying on global optimization techniques. We show that the frequency encoding of memories in SNNs can leverage this paradigm. It enables detecting and learning arbitrary information items, given that they operate in high dimensions. To illustrate the hypothesis, we develop a minimalist model of information processing in layered brain structures and study the emergence of extreme selectivity to multiple stimuli and associative memories. Our results suggest that global optimization of cost functions may be circumvented at different levels of information processing in SNNs, and replaced by chance learning, greatly simplifying the design of AI devices.Frontiers MediaUniversidad Complutense de Madrid20252025-01-0120252025-01-01journal articlehttp://purl.org/coar/resource_type/c_6501VoRhttp://purl.org/coar/version/c_970fb48d4fbd8a85info:eu-repo/semantics/articleapplication/pdfapplication/pdfhttps://hdl.handle.net/20.500.14352/130210reponame:Docta Complutenseinstname:Universidad Complutense de Madrid (UCM)InglésengAgencia Estatal de Investigación http://dx.doi.org/10.13039/501100011033 Plan Estatal de Investigación Científica y Técnica y de Innovación 2021-2023 PID2021-124047NB-I00 FUNDAMENTOS MATEMATICOS DE LA COGNICION PROFUNDA: HACIA EL DESARROLLO DE AGENTES AUTONOMOS BIOINSPIRADOSopen accesshttp://purl.org/coar/access_right/c_abf2Attribution 4.0 Internationalhttp://creativecommons.org/licenses/by/4.0/info:eu-repo/semantics/openAccessoai:docta.ucm.es:20.500.14352/1302102026-06-02T12:44:21Z
dc.title.none.fl_str_mv Blessing of dimensionality in spiking neural networks: the by-chance functional learning
title Blessing of dimensionality in spiking neural networks: the by-chance functional learning
spellingShingle Blessing of dimensionality in spiking neural networks: the by-chance functional learning
Makarov Slizneva, Valeriy
Cibernética matemática
1207.03 Cibernética
title_short Blessing of dimensionality in spiking neural networks: the by-chance functional learning
title_full Blessing of dimensionality in spiking neural networks: the by-chance functional learning
title_fullStr Blessing of dimensionality in spiking neural networks: the by-chance functional learning
title_full_unstemmed Blessing of dimensionality in spiking neural networks: the by-chance functional learning
title_sort Blessing of dimensionality in spiking neural networks: the by-chance functional learning
dc.creator.none.fl_str_mv Makarov Slizneva, Valeriy
Lobov, Sergey
author Makarov Slizneva, Valeriy
author_facet Makarov Slizneva, Valeriy
Lobov, Sergey
author_role author
author2 Lobov, Sergey
author2_role author
dc.contributor.none.fl_str_mv Universidad Complutense de Madrid
dc.subject.none.fl_str_mv Cibernética matemática
1207.03 Cibernética
topic Cibernética matemática
1207.03 Cibernética
description Spiking neural networks (SNNs) have significant potential for a power-efficient neuromorphic AI. However, their training is challenging since most of the learning principles known from artificial neural networks are hardly applicable. Recently, the concept of “blessing of dimensionality” has successfully been used to treat high-dimensional data and representations of reality. It exploits the fundamental trade-off between the complexity and simplicity of statistical sets in high-dimensional spaces without relying on global optimization techniques. We show that the frequency encoding of memories in SNNs can leverage this paradigm. It enables detecting and learning arbitrary information items, given that they operate in high dimensions. To illustrate the hypothesis, we develop a minimalist model of information processing in layered brain structures and study the emergence of extreme selectivity to multiple stimuli and associative memories. Our results suggest that global optimization of cost functions may be circumvented at different levels of information processing in SNNs, and replaced by chance learning, greatly simplifying the design of AI devices.
publishDate 2025
dc.date.none.fl_str_mv 2025
2025-01-01
2025
2025-01-01
dc.type.none.fl_str_mv journal article
http://purl.org/coar/resource_type/c_6501
VoR
http://purl.org/coar/version/c_970fb48d4fbd8a85
dc.type.openaire.fl_str_mv info:eu-repo/semantics/article
format article
dc.identifier.none.fl_str_mv https://hdl.handle.net/20.500.14352/130210
url https://hdl.handle.net/20.500.14352/130210
dc.language.none.fl_str_mv Inglés
eng
language_invalid_str_mv Inglés
language eng
dc.relation.none.fl_str_mv Agencia Estatal de Investigación http://dx.doi.org/10.13039/501100011033 Plan Estatal de Investigación Científica y Técnica y de Innovación 2021-2023 PID2021-124047NB-I00 FUNDAMENTOS MATEMATICOS DE LA COGNICION PROFUNDA: HACIA EL DESARROLLO DE AGENTES AUTONOMOS BIOINSPIRADOS
dc.rights.none.fl_str_mv open access
http://purl.org/coar/access_right/c_abf2
Attribution 4.0 International
http://creativecommons.org/licenses/by/4.0/
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
Attribution 4.0 International
http://creativecommons.org/licenses/by/4.0/
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: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_ 1869425589729886208
score 15,81155

Similar Items