Estimation of the optimal number of neurons in extreme learning machine using simulated annealing and the golden section

Descripción del Articulo

Conferencia de la IX International Conference Days of Applied Mathematics (IX ICDAM)
Detalles Bibliográficos
Autores: Lozada Yavina, Rafael Alejandro, Gelvez-Almeida, E., Mora, M., Huérfano-Maldonado, Y., Salazar-Jurado, E., Martínez-Jeraldo, N., Baldera-Moreno, Y., Tobar, L.
Formato: objeto de conferencia
Fecha de Publicación:2023
Institución:Universidad Tecnológica del Perú
Repositorio:UTP-Institucional
Lenguaje:inglés
OAI Identifier:oai:repositorio.utp.edu.pe:20.500.12867/7739
Enlace del recurso:https://hdl.handle.net/20.500.12867/7739
https://doi.org/10.1088/1742-6596/2515/1/012003
Nivel de acceso:acceso abierto
Materia:Artificial neural networks
Machine learning
Supervised learning
Heuristic optimization methods
https://purl.org/pe-repo/ocde/ford#1.02.00
id UTPD_26f177050fc2b0d87b68e4770a03e1dc
oai_identifier_str oai:repositorio.utp.edu.pe:20.500.12867/7739
network_acronym_str UTPD
network_name_str UTP-Institucional
repository_id_str 4782
dc.title.es_PE.fl_str_mv Estimation of the optimal number of neurons in extreme learning machine using simulated annealing and the golden section
title Estimation of the optimal number of neurons in extreme learning machine using simulated annealing and the golden section
spellingShingle Estimation of the optimal number of neurons in extreme learning machine using simulated annealing and the golden section
Lozada Yavina, Rafael Alejandro
Artificial neural networks
Machine learning
Supervised learning
Heuristic optimization methods
https://purl.org/pe-repo/ocde/ford#1.02.00
title_short Estimation of the optimal number of neurons in extreme learning machine using simulated annealing and the golden section
title_full Estimation of the optimal number of neurons in extreme learning machine using simulated annealing and the golden section
title_fullStr Estimation of the optimal number of neurons in extreme learning machine using simulated annealing and the golden section
title_full_unstemmed Estimation of the optimal number of neurons in extreme learning machine using simulated annealing and the golden section
title_sort Estimation of the optimal number of neurons in extreme learning machine using simulated annealing and the golden section
author Lozada Yavina, Rafael Alejandro
author_facet Lozada Yavina, Rafael Alejandro
Gelvez-Almeida, E.
Mora, M.
Huérfano-Maldonado, Y.
Salazar-Jurado, E.
Martínez-Jeraldo, N.
Baldera-Moreno, Y.
Tobar, L.
author_role author
author2 Gelvez-Almeida, E.
Mora, M.
Huérfano-Maldonado, Y.
Salazar-Jurado, E.
Martínez-Jeraldo, N.
Baldera-Moreno, Y.
Tobar, L.
author2_role author
author
author
author
author
author
author
dc.contributor.author.fl_str_mv Lozada Yavina, Rafael Alejandro
Gelvez-Almeida, E.
Mora, M.
Huérfano-Maldonado, Y.
Salazar-Jurado, E.
Martínez-Jeraldo, N.
Baldera-Moreno, Y.
Tobar, L.
dc.subject.es_PE.fl_str_mv Artificial neural networks
Machine learning
Supervised learning
Heuristic optimization methods
topic Artificial neural networks
Machine learning
Supervised learning
Heuristic optimization methods
https://purl.org/pe-repo/ocde/ford#1.02.00
dc.subject.ocde.es_PE.fl_str_mv https://purl.org/pe-repo/ocde/ford#1.02.00
description Conferencia de la IX International Conference Days of Applied Mathematics (IX ICDAM)
publishDate 2023
dc.date.accessioned.none.fl_str_mv 2023-10-19T18:46:01Z
dc.date.available.none.fl_str_mv 2023-10-19T18:46:01Z
dc.date.issued.fl_str_mv 2023
dc.type.es_PE.fl_str_mv info:eu-repo/semantics/conferenceObject
dc.type.version.es_PE.fl_str_mv info:eu-repo/semantics/publishedVersion
format conferenceObject
status_str publishedVersion
dc.identifier.issn.none.fl_str_mv 1742-6596
dc.identifier.uri.none.fl_str_mv https://hdl.handle.net/20.500.12867/7739
dc.identifier.journal.es_PE.fl_str_mv Journal of Physics: Conference Series
dc.identifier.doi.none.fl_str_mv https://doi.org/10.1088/1742-6596/2515/1/012003
identifier_str_mv 1742-6596
Journal of Physics: Conference Series
url https://hdl.handle.net/20.500.12867/7739
https://doi.org/10.1088/1742-6596/2515/1/012003
dc.language.iso.es_PE.fl_str_mv eng
language eng
dc.relation.ispartofseries.none.fl_str_mv Journal of Physics: Conference Series;vol. 2515
dc.rights.es_PE.fl_str_mv info:eu-repo/semantics/openAccess
dc.rights.uri.es_PE.fl_str_mv http://creativecommons.org/licenses/by/4.0/
eu_rights_str_mv openAccess
rights_invalid_str_mv http://creativecommons.org/licenses/by/4.0/
dc.format.es_PE.fl_str_mv application/pdf
dc.publisher.es_PE.fl_str_mv IOP Publishing
dc.publisher.country.es_PE.fl_str_mv GB
dc.source.es_PE.fl_str_mv Repositorio Institucional - UTP
Universidad Tecnológica del Perú
dc.source.none.fl_str_mv reponame:UTP-Institucional
instname:Universidad Tecnológica del Perú
instacron:UTP
instname_str Universidad Tecnológica del Perú
instacron_str UTP
institution UTP
reponame_str UTP-Institucional
collection UTP-Institucional
bitstream.url.fl_str_mv http://repositorio.utp.edu.pe/bitstream/20.500.12867/7739/3/R.Lozada_Articulo_2023.pdf.txt
http://repositorio.utp.edu.pe/bitstream/20.500.12867/7739/4/R.Lozada_Articulo_2023.pdf.jpg
http://repositorio.utp.edu.pe/bitstream/20.500.12867/7739/5/R.Lozada_Articulo_2023.pdf
http://repositorio.utp.edu.pe/bitstream/20.500.12867/7739/2/license.txt
bitstream.checksum.fl_str_mv 89527288155203e7e0f6910e2c0913d5
6b7b6b58cffdc2deafa937cf64edc78e
4bed8a5e82682ff928317f7b702aff43
8a4605be74aa9ea9d79846c1fba20a33
bitstream.checksumAlgorithm.fl_str_mv MD5
MD5
MD5
MD5
repository.name.fl_str_mv Repositorio Institucional de la Universidad Tecnológica del Perú
repository.mail.fl_str_mv repositorio@utp.edu.pe
_version_ 1817984929830535168
spelling Lozada Yavina, Rafael AlejandroGelvez-Almeida, E.Mora, M.Huérfano-Maldonado, Y.Salazar-Jurado, E.Martínez-Jeraldo, N.Baldera-Moreno, Y.Tobar, L.2023-10-19T18:46:01Z2023-10-19T18:46:01Z20231742-6596https://hdl.handle.net/20.500.12867/7739Journal of Physics: Conference Serieshttps://doi.org/10.1088/1742-6596/2515/1/012003Conferencia de la IX International Conference Days of Applied Mathematics (IX ICDAM)Extreme learning machine is a neural network algorithm widely accepted in the scientific community due to the simplicity of the model and its good results in classification and regression problems; digital image processing, medical diagnosis, and signal recognition are some applications in the field of physics addressed with these neural networks. The algorithm must be executed with an adequate number of neurons in the hidden layer to obtain good results. Identifying the appropriate number of neurons in the hidden layer is an open problem in the extreme learning machine field. The search process has a high computational cost if carried out sequentially, given the complexity of the calculations as the number of neurons increases. In this work, we use the search of the golden section and simulated annealing as heuristic methods to calculate the appropriate number of neurons in the hidden layer of an Extreme Learning Machine; for the experiments, three real databases were used for the classification problem and a synthetic database for the regression problem. The results show that the search for the appropriate number of neurons is accelerated up to 4.5× times with simulated annealing and up to 95.7× times with the golden section search compared to a sequential method in the highest-dimensional database.Campus San Juan de Luriganchoapplication/pdfengIOP PublishingGBJournal of Physics: Conference Series;vol. 2515info:eu-repo/semantics/openAccesshttp://creativecommons.org/licenses/by/4.0/Repositorio Institucional - UTPUniversidad Tecnológica del Perúreponame:UTP-Institucionalinstname:Universidad Tecnológica del Perúinstacron:UTPArtificial neural networksMachine learningSupervised learningHeuristic optimization methodshttps://purl.org/pe-repo/ocde/ford#1.02.00Estimation of the optimal number of neurons in extreme learning machine using simulated annealing and the golden sectioninfo:eu-repo/semantics/conferenceObjectinfo:eu-repo/semantics/publishedVersionTEXTR.Lozada_Articulo_2023.pdf.txtR.Lozada_Articulo_2023.pdf.txtExtracted texttext/plain23428http://repositorio.utp.edu.pe/bitstream/20.500.12867/7739/3/R.Lozada_Articulo_2023.pdf.txt89527288155203e7e0f6910e2c0913d5MD53THUMBNAILR.Lozada_Articulo_2023.pdf.jpgR.Lozada_Articulo_2023.pdf.jpgGenerated Thumbnailimage/jpeg9643http://repositorio.utp.edu.pe/bitstream/20.500.12867/7739/4/R.Lozada_Articulo_2023.pdf.jpg6b7b6b58cffdc2deafa937cf64edc78eMD54ORIGINALR.Lozada_Articulo_2023.pdfR.Lozada_Articulo_2023.pdfapplication/pdf492581http://repositorio.utp.edu.pe/bitstream/20.500.12867/7739/5/R.Lozada_Articulo_2023.pdf4bed8a5e82682ff928317f7b702aff43MD55LICENSElicense.txtlicense.txttext/plain; charset=utf-81748http://repositorio.utp.edu.pe/bitstream/20.500.12867/7739/2/license.txt8a4605be74aa9ea9d79846c1fba20a33MD5220.500.12867/7739oai:repositorio.utp.edu.pe:20.500.12867/77392023-10-19 14:09:36.803Repositorio Institucional de la Universidad Tecnológica del Perúrepositorio@utp.edu.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
score 13.924246
Estimation of the optimal number of neurons in extreme learning machine using simulated annealing and the golden section
Nota importante:
La información contenida en este registro es de entera responsabilidad de la institución que gestiona el repositorio institucional donde esta contenido este documento o set de datos. El CONCYTEC no se hace responsable por los contenidos (publicaciones y/o datos) accesibles a través del Repositorio Nacional Digital de Ciencia, Tecnología e Innovación de Acceso Abierto (ALICIA).

Ejemplares Similares