Optimizing Reservoir Separability in Liquid State Machines for Spatio-Temporal Classification in Neuromorphic Hardware

In this paper, we propose an optimization approach using Particle Swarm Optimization (PSO) to enhance reservoir separability in Liquid State Machines (LSMs) for spatio-temporal classification in neuromorphic systems. By leveraging PSO, our method fine-tunes reservoir parameters, neuron dynamics, and...

ver descrição completa

Detalhes bibliográficos
Autores: Álvarez-Canchila, Óscar I., Espinal, Andrés, Patiño-Saucedo, Alberto, Rostro-Gonzalez, Horacio
Tipo de documento: artigo
Estado:Versão publicada
Data de publicação:2025
País:España
Recursos:Consejo Superior de Investigaciones Científicas (CSIC)
Repositório:DIGITAL.CSIC. Repositorio Institucional del CSIC
OAI Identifier:oai:digital.csic.es:10261/402198
Acesso em linha:http://hdl.handle.net/10261/402198
https://api.elsevier.com/content/abstract/scopus_id/105001133249
Access Level:Acceso aberto
Palavra-chave:Liquid state machine
Neuromorphic computing
Particle swarm optimization
Reservoir computing
SpiNNaker
id ES_f1a7829dca856d091dcfcdb98638eb15
oai_identifier_str oai:digital.csic.es:10261/402198
network_acronym_str ES
network_name_str España
repository_id_str
spelling Optimizing Reservoir Separability in Liquid State Machines for Spatio-Temporal Classification in Neuromorphic HardwareÁlvarez-Canchila, Óscar I.Espinal, AndrésPatiño-Saucedo, AlbertoRostro-Gonzalez, HoracioLiquid state machineNeuromorphic computingParticle swarm optimizationReservoir computingSpiNNakerIn this paper, we propose an optimization approach using Particle Swarm Optimization (PSO) to enhance reservoir separability in Liquid State Machines (LSMs) for spatio-temporal classification in neuromorphic systems. By leveraging PSO, our method fine-tunes reservoir parameters, neuron dynamics, and connectivity patterns, maximizing separability while aligning with the resource constraints typical of neuromorphic hardware. This approach was validated in both software (NEST) and on neuromorphic hardware (SpiNNaker), demonstrating notable results in terms of accuracy and low energy consumption when using SpiNNaker. Specifically, our approach addresses two problems: Frequency Recognition (FR) with five classes and Pattern Recognition (PR) with four, eight, and twelve classes. For instance, in the Mono-objective approach running in NEST, accuracies ranged from 81.09% to 95.52% across the benchmarks under study. The Multi-objective approach outperformed the Mono-objective approach, delivering accuracies ranging from 90.23% to 98.77%, demonstrating its superior scalability for LSM implementations. On the SpiNNaker platform, the mono-objective approach achieved accuracies ranging from 86.20% to 97.70% across the same benchmarks, with the Multi-objective approach further improving accuracies, ranging from 94.42% to 99.52%. These results show that, in addition to slight accuracy improvements, hardware-based implementations offer superior energy efficiency with a lower execution time. For example, SpiNNaker operates at around 1–5 watts per chip, while traditional systems can require 50–100 watts for similar tasks, highlighting the significant energy savings of neuromorphic hardware. These results underscore the scalability and effectiveness of PSO-optimized LSMs on resource-limited neuromorphic platforms, showcasing both improved classification performance and the advantages of energy-efficient processing.Oscar I. Alvarez-Canchila acknowledges the National Council of Humanities, Science and Technology of Mexico (CONAHCYT) for the support provided through scholarship No. 1105105.Peer reviewedMultidisciplinary Digital Publishing InstituteConsejo Nacional de Humanidades, Ciencias y Tecnologías (México)Alvarez-Canchila, Oscar I. [0000-0002-1722-4938]Espinal, Andrés [0000-0003-1552-3210]Patiño-Saucedo, Alberto [0000-0002-3403-5856]Rostro-Gonzalez, Horacio [0000-0001-7530-9027]Consejo Superior de Investigaciones Científicas [https://ror.org/02gfc7t72]202520252025info:eu-repo/semantics/articlehttp://purl.org/coar/resource_type/c_6501Publisher's versioninfo:eu-repo/semantics/publishedVersionapplication/pdfhttp://hdl.handle.net/10261/402198https://api.elsevier.com/content/abstract/scopus_id/105001133249reponame:DIGITAL.CSIC. Repositorio Institucional del CSICinstname:Consejo Superior de Investigaciones Científicas (CSIC)InglésThe underlying dataset has been published as supplementary material of the article in the publisher platform at DOI 10.3390/jlpea15010004https://doi.org/10.3390/jlpea15010004Síinfo:eu-repo/semantics/openAccessoai:digital.csic.es:10261/4021982026-05-22T06:33:51Z
dc.title.none.fl_str_mv Optimizing Reservoir Separability in Liquid State Machines for Spatio-Temporal Classification in Neuromorphic Hardware
title Optimizing Reservoir Separability in Liquid State Machines for Spatio-Temporal Classification in Neuromorphic Hardware
spellingShingle Optimizing Reservoir Separability in Liquid State Machines for Spatio-Temporal Classification in Neuromorphic Hardware
Álvarez-Canchila, Óscar I.
Liquid state machine
Neuromorphic computing
Particle swarm optimization
Reservoir computing
SpiNNaker
title_short Optimizing Reservoir Separability in Liquid State Machines for Spatio-Temporal Classification in Neuromorphic Hardware
title_full Optimizing Reservoir Separability in Liquid State Machines for Spatio-Temporal Classification in Neuromorphic Hardware
title_fullStr Optimizing Reservoir Separability in Liquid State Machines for Spatio-Temporal Classification in Neuromorphic Hardware
title_full_unstemmed Optimizing Reservoir Separability in Liquid State Machines for Spatio-Temporal Classification in Neuromorphic Hardware
title_sort Optimizing Reservoir Separability in Liquid State Machines for Spatio-Temporal Classification in Neuromorphic Hardware
dc.creator.none.fl_str_mv Álvarez-Canchila, Óscar I.
Espinal, Andrés
Patiño-Saucedo, Alberto
Rostro-Gonzalez, Horacio
author Álvarez-Canchila, Óscar I.
author_facet Álvarez-Canchila, Óscar I.
Espinal, Andrés
Patiño-Saucedo, Alberto
Rostro-Gonzalez, Horacio
author_role author
author2 Espinal, Andrés
Patiño-Saucedo, Alberto
Rostro-Gonzalez, Horacio
author2_role author
author
author
dc.contributor.none.fl_str_mv Consejo Nacional de Humanidades, Ciencias y Tecnologías (México)
Alvarez-Canchila, Oscar I. [0000-0002-1722-4938]
Espinal, Andrés [0000-0003-1552-3210]
Patiño-Saucedo, Alberto [0000-0002-3403-5856]
Rostro-Gonzalez, Horacio [0000-0001-7530-9027]
Consejo Superior de Investigaciones Científicas [https://ror.org/02gfc7t72]
dc.subject.none.fl_str_mv Liquid state machine
Neuromorphic computing
Particle swarm optimization
Reservoir computing
SpiNNaker
topic Liquid state machine
Neuromorphic computing
Particle swarm optimization
Reservoir computing
SpiNNaker
description In this paper, we propose an optimization approach using Particle Swarm Optimization (PSO) to enhance reservoir separability in Liquid State Machines (LSMs) for spatio-temporal classification in neuromorphic systems. By leveraging PSO, our method fine-tunes reservoir parameters, neuron dynamics, and connectivity patterns, maximizing separability while aligning with the resource constraints typical of neuromorphic hardware. This approach was validated in both software (NEST) and on neuromorphic hardware (SpiNNaker), demonstrating notable results in terms of accuracy and low energy consumption when using SpiNNaker. Specifically, our approach addresses two problems: Frequency Recognition (FR) with five classes and Pattern Recognition (PR) with four, eight, and twelve classes. For instance, in the Mono-objective approach running in NEST, accuracies ranged from 81.09% to 95.52% across the benchmarks under study. The Multi-objective approach outperformed the Mono-objective approach, delivering accuracies ranging from 90.23% to 98.77%, demonstrating its superior scalability for LSM implementations. On the SpiNNaker platform, the mono-objective approach achieved accuracies ranging from 86.20% to 97.70% across the same benchmarks, with the Multi-objective approach further improving accuracies, ranging from 94.42% to 99.52%. These results show that, in addition to slight accuracy improvements, hardware-based implementations offer superior energy efficiency with a lower execution time. For example, SpiNNaker operates at around 1–5 watts per chip, while traditional systems can require 50–100 watts for similar tasks, highlighting the significant energy savings of neuromorphic hardware. These results underscore the scalability and effectiveness of PSO-optimized LSMs on resource-limited neuromorphic platforms, showcasing both improved classification performance and the advantages of energy-efficient processing.
publishDate 2025
dc.date.none.fl_str_mv 2025
2025
2025
dc.type.none.fl_str_mv info:eu-repo/semantics/article
http://purl.org/coar/resource_type/c_6501
Publisher's version
info:eu-repo/semantics/publishedVersion
format article
status_str publishedVersion
dc.identifier.none.fl_str_mv http://hdl.handle.net/10261/402198
https://api.elsevier.com/content/abstract/scopus_id/105001133249
url http://hdl.handle.net/10261/402198
https://api.elsevier.com/content/abstract/scopus_id/105001133249
dc.language.none.fl_str_mv Inglés
language_invalid_str_mv Inglés
dc.relation.none.fl_str_mv The underlying dataset has been published as supplementary material of the article in the publisher platform at DOI 10.3390/jlpea15010004
https://doi.org/10.3390/jlpea15010004
Sí
dc.rights.none.fl_str_mv info:eu-repo/semantics/openAccess
eu_rights_str_mv openAccess
dc.format.none.fl_str_mv application/pdf
dc.publisher.none.fl_str_mv Multidisciplinary Digital Publishing Institute
publisher.none.fl_str_mv Multidisciplinary Digital Publishing Institute
dc.source.none.fl_str_mv reponame:DIGITAL.CSIC. Repositorio Institucional del CSIC
instname:Consejo Superior de Investigaciones Científicas (CSIC)
instname_str Consejo Superior de Investigaciones Científicas (CSIC)
reponame_str DIGITAL.CSIC. Repositorio Institucional del CSIC
collection DIGITAL.CSIC. Repositorio Institucional del CSIC
repository.name.fl_str_mv
repository.mail.fl_str_mv
_version_ 1869424176687742976
score 15.811543

Registros relacionados