Please use this identifier to cite or link to this item:
https://hdl.handle.net/10316/112074
DC Field | Value | Language |
---|---|---|
dc.contributor.author | Branquinho, Henrique | - |
dc.contributor.author | Lourenço, Nuno | - |
dc.contributor.author | Costa, Ernesto | - |
dc.date.accessioned | 2024-01-22T09:22:29Z | - |
dc.date.available | 2024-01-22T09:22:29Z | - |
dc.date.issued | 2023-05-18 | - |
dc.identifier.uri | https://hdl.handle.net/10316/112074 | - |
dc.description.abstract | Spiking Neural Networks (SNNs) have attracted recent interest due to their energy efficiency and biological plausibility. However, the performance of SNNs still lags behind traditional Artificial Neural Networks (ANNs), as there is no consensus on the best learning algorithm for SNNs. Best-performing SNNs are based on ANN to SNN conversion or learning with spike-based backpropagation through surrogate gradients. The focus of recent research has been on developing and testing different learning strategies, with hand-tailored architectures and parameter tuning. Neuroevolution (NE), has proven successful as a way to automatically design ANNs and tune parameters, but its applications to SNNs are still at an early stage. DENSER is a NE framework for the automatic design and parametrization of ANNs, based on the principles of Genetic Algorithms (GA) and Structured Grammatical Evolution (SGE). In this paper, we propose SPENSER, a NE framework for SNN generation based on DENSER, for image classification on the MNIST and Fashion-MNIST datasets. SPENSER generates competitive performing networks with a test accuracy of 99.42% and 91.65% respectively. | pt |
dc.description.sponsorship | Portuguese Recovery and Resilience Plan (PRR) through project (C645008882-00000055) and grant 2022.11314.BD. | pt |
dc.language.iso | eng | pt |
dc.publisher | Association for Computing Machinery, Inc | pt |
dc.relation | UIDB/00326/2020 | pt |
dc.relation | UIDP/00326/2020 | pt |
dc.rights | openAccess | pt |
dc.rights.uri | http://creativecommons.org/licenses/by/4.0/ | pt |
dc.subject | spiking neural networks | pt |
dc.subject | neuroevolution | pt |
dc.subject | DENSER | pt |
dc.subject | computer vision | pt |
dc.title | SPENSER: Towards a NeuroEvolutionary Approach for Convolutional Spiking Neural Networks | pt |
dc.type | article | - |
degois.publication.firstPage | 2115 | pt |
degois.publication.lastPage | 2122 | pt |
degois.publication.title | GECCO 2023 Companion - Proceedings of the 2023 Genetic and Evolutionary Computation Conference Companion | pt |
dc.peerreviewed | yes | pt |
dc.identifier.doi | 10.1145/3583133.3596399 | pt |
dc.date.embargo | 2023-05-18 | * |
uc.date.periodoEmbargo | 0 | pt |
item.fulltext | Com Texto completo | - |
item.grantfulltext | open | - |
item.languageiso639-1 | en | - |
item.cerifentitytype | Publications | - |
item.openairetype | article | - |
item.openairecristype | http://purl.org/coar/resource_type/c_18cf | - |
crisitem.project.grantno | CISUC- CENTRE FOR INFORMATICS AND SYSTEMS OF THE UNIVERSITY OF COIMBRA | - |
crisitem.project.grantno | CENTRE FOR INFORMATICS AND SYSTEMS OF THE UNIVERSITY OF COIMBRA | - |
crisitem.author.researchunit | CISUC - Centre for Informatics and Systems of the University of Coimbra | - |
crisitem.author.parentresearchunit | Faculty of Sciences and Technology | - |
crisitem.author.orcid | 0000-0002-8460-4033 | - |
Appears in Collections: | I&D CISUC - Artigos em Revistas Internacionais FCTUC Eng.Informática - Artigos em Revistas Internacionais |
Files in This Item:
File | Description | Size | Format | |
---|---|---|---|---|
SPENSER Towards a NeuroEvolutionary Approach for Convolutional Spiking Neural Networks.pdf | 3.04 MB | Adobe PDF | View/Open |
Page view(s)
48
checked on Sep 25, 2024
Download(s)
36
checked on Sep 25, 2024
Google ScholarTM
Check
Altmetric
Altmetric
This item is licensed under a Creative Commons License