A Study of Generalization and Fitness Landscapes for Neuroevolution

Detalhes bibliográficos
Autor(a) principal: Rodrigues, Nuno M.
Data de Publicação: 2020
Outros Autores: Silva, Sara, Vanneschi, Leonardo
Tipo de documento: Artigo
Idioma: eng
Título da fonte: Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos)
Texto Completo: http://hdl.handle.net/10362/100685
Resumo: Rodrigues, N. M., Silva, S., & Vanneschi, L. (2020). A Study of Generalization and Fitness Landscapes for Neuroevolution. IEEE Access, 8, 108216-108234. [9113453]. https://doi.org/10.1109/ACCESS.2020.3001505
id RCAP_9a79c73295f954f0c8540c778bd8b67a
oai_identifier_str oai:run.unl.pt:10362/100685
network_acronym_str RCAP
network_name_str Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos)
repository_id_str 7160
spelling A Study of Generalization and Fitness Landscapes for NeuroevolutionAutocorrelationconvolutional neural networksdensity cloudsentropic measure of ruggednessfitness cloudsfitness landscapesgeneralizationneuroevolutionoverfittingComputer Science(all)Materials Science(all)Engineering(all)Rodrigues, N. M., Silva, S., & Vanneschi, L. (2020). A Study of Generalization and Fitness Landscapes for Neuroevolution. IEEE Access, 8, 108216-108234. [9113453]. https://doi.org/10.1109/ACCESS.2020.3001505Fitness landscapes are a useful concept for studying the dynamics of meta-heuristics. In the last two decades, they have been successfully used for estimating the optimization capabilities of different flavors of evolutionary algorithms, including genetic algorithms and genetic programming. However, so far they have not been used for studying the performance of machine learning algorithms on unseen data, and they have not been applied to studying neuroevolution landscapes. This paper fills these gaps by applying fitness landscapes to neuroevolution, and using this concept to infer useful information about the learning and generalization ability of the machine learning method. For this task, we use a grammar-based approach to generate convolutional neural networks, and we study the dynamics of three different mutations used to evolve them. To characterize fitness landscapes, we study autocorrelation, entropic measure of ruggedness, and fitness clouds. Also, we propose the use of two additional evaluation measures: density clouds and overfitting measure. The results show that these measures are appropriate for estimating both the learning and the generalization ability of the considered neuroevolution configurations.NOVA Information Management School (NOVA IMS)Information Management Research Center (MagIC) - NOVA Information Management SchoolRUNRodrigues, Nuno M.Silva, SaraVanneschi, Leonardo2020-07-10T22:22:19Z2020-06-222020-06-22T00:00:00Zinfo:eu-repo/semantics/publishedVersioninfo:eu-repo/semantics/article19application/pdfhttp://hdl.handle.net/10362/100685engPURE: 18961711https://doi.org/10.1109/ACCESS.2020.3001505info:eu-repo/semantics/openAccessreponame:Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos)instname:Agência para a Sociedade do Conhecimento (UMIC) - FCT - Sociedade da Informaçãoinstacron:RCAAP2024-03-11T04:47:04Zoai:run.unl.pt:10362/100685Portal AgregadorONGhttps://www.rcaap.pt/oai/openaireopendoar:71602024-03-20T03:39:24.733396Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos) - Agência para a Sociedade do Conhecimento (UMIC) - FCT - Sociedade da Informaçãofalse
dc.title.none.fl_str_mv A Study of Generalization and Fitness Landscapes for Neuroevolution
title A Study of Generalization and Fitness Landscapes for Neuroevolution
spellingShingle A Study of Generalization and Fitness Landscapes for Neuroevolution
Rodrigues, Nuno M.
Autocorrelation
convolutional neural networks
density clouds
entropic measure of ruggedness
fitness clouds
fitness landscapes
generalization
neuroevolution
overfitting
Computer Science(all)
Materials Science(all)
Engineering(all)
title_short A Study of Generalization and Fitness Landscapes for Neuroevolution
title_full A Study of Generalization and Fitness Landscapes for Neuroevolution
title_fullStr A Study of Generalization and Fitness Landscapes for Neuroevolution
title_full_unstemmed A Study of Generalization and Fitness Landscapes for Neuroevolution
title_sort A Study of Generalization and Fitness Landscapes for Neuroevolution
author Rodrigues, Nuno M.
author_facet Rodrigues, Nuno M.
Silva, Sara
Vanneschi, Leonardo
author_role author
author2 Silva, Sara
Vanneschi, Leonardo
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 Rodrigues, Nuno M.
Silva, Sara
Vanneschi, Leonardo
dc.subject.por.fl_str_mv Autocorrelation
convolutional neural networks
density clouds
entropic measure of ruggedness
fitness clouds
fitness landscapes
generalization
neuroevolution
overfitting
Computer Science(all)
Materials Science(all)
Engineering(all)
topic Autocorrelation
convolutional neural networks
density clouds
entropic measure of ruggedness
fitness clouds
fitness landscapes
generalization
neuroevolution
overfitting
Computer Science(all)
Materials Science(all)
Engineering(all)
description Rodrigues, N. M., Silva, S., & Vanneschi, L. (2020). A Study of Generalization and Fitness Landscapes for Neuroevolution. IEEE Access, 8, 108216-108234. [9113453]. https://doi.org/10.1109/ACCESS.2020.3001505
publishDate 2020
dc.date.none.fl_str_mv 2020-07-10T22:22:19Z
2020-06-22
2020-06-22T00:00:00Z
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/10362/100685
url http://hdl.handle.net/10362/100685
dc.language.iso.fl_str_mv eng
language eng
dc.relation.none.fl_str_mv PURE: 18961711
https://doi.org/10.1109/ACCESS.2020.3001505
dc.rights.driver.fl_str_mv info:eu-repo/semantics/openAccess
eu_rights_str_mv openAccess
dc.format.none.fl_str_mv 19
application/pdf
dc.source.none.fl_str_mv reponame:Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos)
instname:Agência para a Sociedade do Conhecimento (UMIC) - FCT - Sociedade da Informação
instacron:RCAAP
instname_str Agência para a Sociedade do Conhecimento (UMIC) - FCT - Sociedade da Informação
instacron_str RCAAP
institution RCAAP
reponame_str Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos)
collection Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos)
repository.name.fl_str_mv Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos) - Agência para a Sociedade do Conhecimento (UMIC) - FCT - Sociedade da Informação
repository.mail.fl_str_mv
_version_ 1799138009970376704

Registros relacionados