Harmony Search-Based Approaches for Fine-Tuning Deep Belief Networks

Detalhes bibliográficos
Autor(a) principal: Rodrigues, Douglas [UNESP]
Data de Publicação: 2023
Outros Autores: Roder, Mateus [UNESP], Passos, Leandro Aparecido, Rosa, Gustavo Henrique de [UNESP], Papa, João Paulo [UNESP], Geem, Zong Woo
Tipo de documento: Capítulo de livro
Idioma: eng
Título da fonte: Repositório Institucional da UNESP
Texto Completo: http://dx.doi.org/10.1007/978-3-031-22371-6_5
http://hdl.handle.net/11449/249857
Resumo: Harmony Search (HS) is a metaheuristic algorithm inspired by the musical composition process, precisely the composition of harmonies, i.e., the chain of different musical notes. The algorithm’s simplicity allows several points to improve to explore the entire search space efficiently. This work aims to compare different HS variants in image restoration using Deep Belief Networks (DBN). We compared standard HS against five variants: Improved Harmony Search (IHS), Self-adaptive Global Best Harmony Search (SGHS), Global-best Harmony Search (GHS), Novel Global Harmony Search (NGHS), and Global Harmony Search with Generalized Opposition-based learning (GOGHS). Experiments in public datasets for binary image reconstruction highlighted that HS and its variants obtained superior results than a random search used as a baseline. Also, it was found that the GHS variant is inferior to the others for some cases.
id UNSP_22493731f7f5f3ded0b9d38111c8f1f8
oai_identifier_str oai:repositorio.unesp.br:11449/249857
network_acronym_str UNSP
network_name_str Repositório Institucional da UNESP
repository_id_str 2946
spelling Harmony Search-Based Approaches for Fine-Tuning Deep Belief NetworksDeep Belief NetworksHarmony SearchMetaheuristic optimizationHarmony Search (HS) is a metaheuristic algorithm inspired by the musical composition process, precisely the composition of harmonies, i.e., the chain of different musical notes. The algorithm’s simplicity allows several points to improve to explore the entire search space efficiently. This work aims to compare different HS variants in image restoration using Deep Belief Networks (DBN). We compared standard HS against five variants: Improved Harmony Search (IHS), Self-adaptive Global Best Harmony Search (SGHS), Global-best Harmony Search (GHS), Novel Global Harmony Search (NGHS), and Global Harmony Search with Generalized Opposition-based learning (GOGHS). Experiments in public datasets for binary image reconstruction highlighted that HS and its variants obtained superior results than a random search used as a baseline. Also, it was found that the GHS variant is inferior to the others for some cases.Department of Computing São Paulo State UniversitySchool of Engineering and Informatics University of WolverhamptonDepartment of Energy IT Gachon UniversityDepartment of Computing São Paulo State UniversityUniversidade Estadual Paulista (UNESP)University of WolverhamptonGachon UniversityRodrigues, Douglas [UNESP]Roder, Mateus [UNESP]Passos, Leandro AparecidoRosa, Gustavo Henrique de [UNESP]Papa, João Paulo [UNESP]Geem, Zong Woo2023-07-29T16:11:04Z2023-07-29T16:11:04Z2023-01-01info:eu-repo/semantics/publishedVersioninfo:eu-repo/semantics/bookPart105-118http://dx.doi.org/10.1007/978-3-031-22371-6_5Intelligent Systems Reference Library, v. 236, p. 105-118.1868-44081868-4394http://hdl.handle.net/11449/24985710.1007/978-3-031-22371-6_52-s2.0-85152447198Scopusreponame:Repositório Institucional da UNESPinstname:Universidade Estadual Paulista (UNESP)instacron:UNESPengIntelligent Systems Reference Libraryinfo:eu-repo/semantics/openAccess2024-04-23T16:11:01Zoai:repositorio.unesp.br:11449/249857Repositório InstitucionalPUBhttp://repositorio.unesp.br/oai/requestopendoar:29462024-04-23T16:11:01Repositório Institucional da UNESP - Universidade Estadual Paulista (UNESP)false
dc.title.none.fl_str_mv Harmony Search-Based Approaches for Fine-Tuning Deep Belief Networks
title Harmony Search-Based Approaches for Fine-Tuning Deep Belief Networks
spellingShingle Harmony Search-Based Approaches for Fine-Tuning Deep Belief Networks
Rodrigues, Douglas [UNESP]
Deep Belief Networks
Harmony Search
Metaheuristic optimization
title_short Harmony Search-Based Approaches for Fine-Tuning Deep Belief Networks
title_full Harmony Search-Based Approaches for Fine-Tuning Deep Belief Networks
title_fullStr Harmony Search-Based Approaches for Fine-Tuning Deep Belief Networks
title_full_unstemmed Harmony Search-Based Approaches for Fine-Tuning Deep Belief Networks
title_sort Harmony Search-Based Approaches for Fine-Tuning Deep Belief Networks
author Rodrigues, Douglas [UNESP]
author_facet Rodrigues, Douglas [UNESP]
Roder, Mateus [UNESP]
Passos, Leandro Aparecido
Rosa, Gustavo Henrique de [UNESP]
Papa, João Paulo [UNESP]
Geem, Zong Woo
author_role author
author2 Roder, Mateus [UNESP]
Passos, Leandro Aparecido
Rosa, Gustavo Henrique de [UNESP]
Papa, João Paulo [UNESP]
Geem, Zong Woo
author2_role author
author
author
author
author
dc.contributor.none.fl_str_mv Universidade Estadual Paulista (UNESP)
University of Wolverhampton
Gachon University
dc.contributor.author.fl_str_mv Rodrigues, Douglas [UNESP]
Roder, Mateus [UNESP]
Passos, Leandro Aparecido
Rosa, Gustavo Henrique de [UNESP]
Papa, João Paulo [UNESP]
Geem, Zong Woo
dc.subject.por.fl_str_mv Deep Belief Networks
Harmony Search
Metaheuristic optimization
topic Deep Belief Networks
Harmony Search
Metaheuristic optimization
description Harmony Search (HS) is a metaheuristic algorithm inspired by the musical composition process, precisely the composition of harmonies, i.e., the chain of different musical notes. The algorithm’s simplicity allows several points to improve to explore the entire search space efficiently. This work aims to compare different HS variants in image restoration using Deep Belief Networks (DBN). We compared standard HS against five variants: Improved Harmony Search (IHS), Self-adaptive Global Best Harmony Search (SGHS), Global-best Harmony Search (GHS), Novel Global Harmony Search (NGHS), and Global Harmony Search with Generalized Opposition-based learning (GOGHS). Experiments in public datasets for binary image reconstruction highlighted that HS and its variants obtained superior results than a random search used as a baseline. Also, it was found that the GHS variant is inferior to the others for some cases.
publishDate 2023
dc.date.none.fl_str_mv 2023-07-29T16:11:04Z
2023-07-29T16:11:04Z
2023-01-01
dc.type.status.fl_str_mv info:eu-repo/semantics/publishedVersion
dc.type.driver.fl_str_mv info:eu-repo/semantics/bookPart
format bookPart
status_str publishedVersion
dc.identifier.uri.fl_str_mv http://dx.doi.org/10.1007/978-3-031-22371-6_5
Intelligent Systems Reference Library, v. 236, p. 105-118.
1868-4408
1868-4394
http://hdl.handle.net/11449/249857
10.1007/978-3-031-22371-6_5
2-s2.0-85152447198
url http://dx.doi.org/10.1007/978-3-031-22371-6_5
http://hdl.handle.net/11449/249857
identifier_str_mv Intelligent Systems Reference Library, v. 236, p. 105-118.
1868-4408
1868-4394
10.1007/978-3-031-22371-6_5
2-s2.0-85152447198
dc.language.iso.fl_str_mv eng
language eng
dc.relation.none.fl_str_mv Intelligent Systems Reference Library
dc.rights.driver.fl_str_mv info:eu-repo/semantics/openAccess
eu_rights_str_mv openAccess
dc.format.none.fl_str_mv 105-118
dc.source.none.fl_str_mv Scopus
reponame:Repositório Institucional da UNESP
instname:Universidade Estadual Paulista (UNESP)
instacron:UNESP
instname_str Universidade Estadual Paulista (UNESP)
instacron_str UNESP
institution UNESP
reponame_str Repositório Institucional da UNESP
collection Repositório Institucional da UNESP
repository.name.fl_str_mv Repositório Institucional da UNESP - Universidade Estadual Paulista (UNESP)
repository.mail.fl_str_mv
_version_ 1799965464761204736

Registros relacionados