Neuroevolution with box mutation

Bibliographic Details
Main Author: Santos, Frederico J. J. B.
Publication Date: 2023
Other Authors: Gonçalves, Ivo, Castelli, Mauro
Format: Article
Language: eng
Source: Repositórios Científicos de Acesso Aberto de Portugal (RCAAP)
Download full: http://hdl.handle.net/10362/157226
Summary: Santos, F. J. J. B., Gonçalves, I., & Castelli, M. (2023). Neuroevolution with box mutation: An adaptive and modular framework for evolving deep neural networks. Applied Soft Computing, 147(November), 1-15. [110767]. https://doi.org/10.1016/j.asoc.2023.110767 --- Funding: This work is funded by national funds through the FCT - Foundation for Science and Technology, I.P., within the scope of the projects CISUC - UID/CEC/00326/2020, UIDB/04152/2020 - Centro de Investigação em Gestão de Informação (MagIC)/NOVA IMS, and by European Social Fund, through the Regional Operational Program Centro 2020 .
id RCAP_a8cb646ad5a2aa88873dd5b23d7c9c2d
oai_identifier_str oai:run.unl.pt:10362/157226
network_acronym_str RCAP
network_name_str Repositórios Científicos de Acesso Aberto de Portugal (RCAAP)
repository_id_str https://opendoar.ac.uk/repository/7160
spelling Neuroevolution with box mutationAn adaptive and modular framework for evolving deep neural networksNeuroevolutionEvolutionary deep learningNeural architecture searchSupervised learningSoftwareSantos, F. J. J. B., Gonçalves, I., & Castelli, M. (2023). Neuroevolution with box mutation: An adaptive and modular framework for evolving deep neural networks. Applied Soft Computing, 147(November), 1-15. [110767]. https://doi.org/10.1016/j.asoc.2023.110767 --- Funding: This work is funded by national funds through the FCT - Foundation for Science and Technology, I.P., within the scope of the projects CISUC - UID/CEC/00326/2020, UIDB/04152/2020 - Centro de Investigação em Gestão de Informação (MagIC)/NOVA IMS, and by European Social Fund, through the Regional Operational Program Centro 2020 .The pursuit of self-evolving neural networks has driven the emerging field of Evolutionary Deep Learning, which combines the strengths of Deep Learning and Evolutionary Computation. This work presents a novel method for evolving deep neural networks by adapting the principles of Geometric Semantic Genetic Programming, a subfield of Genetic Programming, and Semantic Learning Machine. Our approach integrates evolution seamlessly through natural selection with the optimization power of backpropagation in deep learning, enabling the incremental growth of neural networks’ neurons across generations. By evolving neural networks that achieve nearly 89% accuracy on the CIFAR-10 dataset with relatively few parameters, our method demonstrates remarkable efficiency, evolving in GPU minutes compared to the field standard of GPU days.NOVA Information Management School (NOVA IMS)Information Management Research Center (MagIC) - NOVA Information Management SchoolRUNSantos, Frederico J. J. B.Gonçalves, IvoCastelli, Mauro2023-09-01T22:16:01Z2023-11-012023-11-01T00:00:00Zinfo:eu-repo/semantics/publishedVersioninfo:eu-repo/semantics/article15application/pdfhttp://hdl.handle.net/10362/157226eng1568-4946PURE: 70324693https://doi.org/10.1016/j.asoc.2023.110767info:eu-repo/semantics/openAccessreponame:Repositórios Científicos de Acesso Aberto de Portugal (RCAAP)instname:FCCN, serviços digitais da FCT – Fundação para a Ciência e a Tecnologiainstacron:RCAAP2024-05-22T18:14:00Zoai:run.unl.pt:10362/157226Portal AgregadorONGhttps://www.rcaap.pt/oai/openaireinfo@rcaap.ptopendoar:https://opendoar.ac.uk/repository/71602025-05-28T17:44:22.120701Repositórios Científicos de Acesso Aberto de Portugal (RCAAP) - FCCN, serviços digitais da FCT – Fundação para a Ciência e a Tecnologiafalse
dc.title.none.fl_str_mv Neuroevolution with box mutation
An adaptive and modular framework for evolving deep neural networks
title Neuroevolution with box mutation
spellingShingle Neuroevolution with box mutation
Santos, Frederico J. J. B.
Neuroevolution
Evolutionary deep learning
Neural architecture search
Supervised learning
Software
title_short Neuroevolution with box mutation
title_full Neuroevolution with box mutation
title_fullStr Neuroevolution with box mutation
title_full_unstemmed Neuroevolution with box mutation
title_sort Neuroevolution with box mutation
author Santos, Frederico J. J. B.
author_facet Santos, Frederico J. J. B.
Gonçalves, Ivo
Castelli, Mauro
author_role author
author2 Gonçalves, Ivo
Castelli, Mauro
author2_role author
author
dc.contributor.none.fl_str_mv NOVA Information Management School (NOVA IMS)
Information Management Research Center (MagIC) - NOVA Information Management School
RUN
dc.contributor.author.fl_str_mv Santos, Frederico J. J. B.
Gonçalves, Ivo
Castelli, Mauro
dc.subject.por.fl_str_mv Neuroevolution
Evolutionary deep learning
Neural architecture search
Supervised learning
Software
topic Neuroevolution
Evolutionary deep learning
Neural architecture search
Supervised learning
Software
description Santos, F. J. J. B., Gonçalves, I., & Castelli, M. (2023). Neuroevolution with box mutation: An adaptive and modular framework for evolving deep neural networks. Applied Soft Computing, 147(November), 1-15. [110767]. https://doi.org/10.1016/j.asoc.2023.110767 --- Funding: This work is funded by national funds through the FCT - Foundation for Science and Technology, I.P., within the scope of the projects CISUC - UID/CEC/00326/2020, UIDB/04152/2020 - Centro de Investigação em Gestão de Informação (MagIC)/NOVA IMS, and by European Social Fund, through the Regional Operational Program Centro 2020 .
publishDate 2023
dc.date.none.fl_str_mv 2023-09-01T22:16:01Z
2023-11-01
2023-11-01T00:00:00Z
dc.type.status.fl_str_mv info:eu-repo/semantics/publishedVersion
dc.type.driver.fl_str_mv info:eu-repo/semantics/article
format article
status_str publishedVersion
dc.identifier.uri.fl_str_mv http://hdl.handle.net/10362/157226
url http://hdl.handle.net/10362/157226
dc.language.iso.fl_str_mv eng
language eng
dc.relation.none.fl_str_mv 1568-4946
PURE: 70324693
https://doi.org/10.1016/j.asoc.2023.110767
dc.rights.driver.fl_str_mv info:eu-repo/semantics/openAccess
eu_rights_str_mv openAccess
dc.format.none.fl_str_mv 15
application/pdf
dc.source.none.fl_str_mv reponame:Repositórios Científicos de Acesso Aberto de Portugal (RCAAP)
instname:FCCN, serviços digitais da FCT – Fundação para a Ciência e a Tecnologia
instacron:RCAAP
instname_str FCCN, serviços digitais da FCT – Fundação para a Ciência e a Tecnologia
instacron_str RCAAP
institution RCAAP
reponame_str Repositórios Científicos de Acesso Aberto de Portugal (RCAAP)
collection Repositórios Científicos de Acesso Aberto de Portugal (RCAAP)
repository.name.fl_str_mv Repositórios Científicos de Acesso Aberto de Portugal (RCAAP) - FCCN, serviços digitais da FCT – Fundação para a Ciência e a Tecnologia
repository.mail.fl_str_mv info@rcaap.pt
_version_ 1833596929183842304

Similar Items