A comparison between two approaches to optimize weights of connections in artificial neural networks
Autor(a) principal: | |
---|---|
Data de Publicação: | 2021 |
Tipo de documento: | Artigo |
Idioma: | eng |
Título da fonte: | Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos) |
Texto Completo: | http://hdl.handle.net/10400.14/36530 |
Resumo: | Artificial neural networks (ANNs) have been used for estimation in numerous areas. Raising the accuracy of ANNs is always one of the important challenges, which is generally defined as a non-linear optimization problem. The aim of this optimization is to find better values for the weights of the connections and biases in ANN because they seriously affect the efficiency. This study uses two approaches to do such optimization in an ANN. For this aim, we create a feed-forward backpropagation ANN using the functions of MATLAB’s deep learning toolbox. To improve its accuracy, in the first approach, we use the Levenberg—Marquardt algorithm (LMA) for training, which is available in MATLAB’s deep learning toolbox. In the second approach, we optimize the values of weights and biases of ANN with Genetic Algorithm (GA) and Particle Swarm Optimization (PSO), available in MATLAB’s global optimization toolbox. Then, we assess the accuracy of estimation for the trained ANNs. In this way, for the first time in the literature, we compare these methods for the optimization of an ANN. The used data sets are also available in MATLAB. Based on the acquired results, in some data sets, training with LMA, and for some others training with PSO cause the best results, however, training with LMA is faster, significantly. Although the used approaches and the obtained conclusions are beneficial for researchers that work in this field, they have some limitations. For instance, since only the functions and data sets from MATLAB are used, it can only serve as an example for researchers. |
id |
RCAP_80c6d82cee636e5fdfec9dda24d5764e |
---|---|
oai_identifier_str |
oai:repositorio.ucp.pt:10400.14/36530 |
network_acronym_str |
RCAP |
network_name_str |
Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos) |
repository_id_str |
7160 |
spelling |
A comparison between two approaches to optimize weights of connections in artificial neural networksArtificial neural networksGenetic algorithmParticle swarm optimizationMATLAB’s toolboxesArtificial neural networks (ANNs) have been used for estimation in numerous areas. Raising the accuracy of ANNs is always one of the important challenges, which is generally defined as a non-linear optimization problem. The aim of this optimization is to find better values for the weights of the connections and biases in ANN because they seriously affect the efficiency. This study uses two approaches to do such optimization in an ANN. For this aim, we create a feed-forward backpropagation ANN using the functions of MATLAB’s deep learning toolbox. To improve its accuracy, in the first approach, we use the Levenberg—Marquardt algorithm (LMA) for training, which is available in MATLAB’s deep learning toolbox. In the second approach, we optimize the values of weights and biases of ANN with Genetic Algorithm (GA) and Particle Swarm Optimization (PSO), available in MATLAB’s global optimization toolbox. Then, we assess the accuracy of estimation for the trained ANNs. In this way, for the first time in the literature, we compare these methods for the optimization of an ANN. The used data sets are also available in MATLAB. Based on the acquired results, in some data sets, training with LMA, and for some others training with PSO cause the best results, however, training with LMA is faster, significantly. Although the used approaches and the obtained conclusions are beneficial for researchers that work in this field, they have some limitations. For instance, since only the functions and data sets from MATLAB are used, it can only serve as an example for researchers.Veritati - Repositório Institucional da Universidade Católica PortuguesaTeymourifar, Aydin2022-01-21T15:35:33Z2021-072021-07-01T00:00:00Zinfo:eu-repo/semantics/publishedVersioninfo:eu-repo/semantics/articleapplication/pdfhttp://hdl.handle.net/10400.14/36530eng2331-644610.13189/ujam.2021.090201info: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:RCAAP2023-07-12T17:42:00Zoai:repositorio.ucp.pt:10400.14/36530Portal AgregadorONGhttps://www.rcaap.pt/oai/openaireopendoar:71602024-03-19T18:29:41.549079Repositório 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 comparison between two approaches to optimize weights of connections in artificial neural networks |
title |
A comparison between two approaches to optimize weights of connections in artificial neural networks |
spellingShingle |
A comparison between two approaches to optimize weights of connections in artificial neural networks Teymourifar, Aydin Artificial neural networks Genetic algorithm Particle swarm optimization MATLAB’s toolboxes |
title_short |
A comparison between two approaches to optimize weights of connections in artificial neural networks |
title_full |
A comparison between two approaches to optimize weights of connections in artificial neural networks |
title_fullStr |
A comparison between two approaches to optimize weights of connections in artificial neural networks |
title_full_unstemmed |
A comparison between two approaches to optimize weights of connections in artificial neural networks |
title_sort |
A comparison between two approaches to optimize weights of connections in artificial neural networks |
author |
Teymourifar, Aydin |
author_facet |
Teymourifar, Aydin |
author_role |
author |
dc.contributor.none.fl_str_mv |
Veritati - Repositório Institucional da Universidade Católica Portuguesa |
dc.contributor.author.fl_str_mv |
Teymourifar, Aydin |
dc.subject.por.fl_str_mv |
Artificial neural networks Genetic algorithm Particle swarm optimization MATLAB’s toolboxes |
topic |
Artificial neural networks Genetic algorithm Particle swarm optimization MATLAB’s toolboxes |
description |
Artificial neural networks (ANNs) have been used for estimation in numerous areas. Raising the accuracy of ANNs is always one of the important challenges, which is generally defined as a non-linear optimization problem. The aim of this optimization is to find better values for the weights of the connections and biases in ANN because they seriously affect the efficiency. This study uses two approaches to do such optimization in an ANN. For this aim, we create a feed-forward backpropagation ANN using the functions of MATLAB’s deep learning toolbox. To improve its accuracy, in the first approach, we use the Levenberg—Marquardt algorithm (LMA) for training, which is available in MATLAB’s deep learning toolbox. In the second approach, we optimize the values of weights and biases of ANN with Genetic Algorithm (GA) and Particle Swarm Optimization (PSO), available in MATLAB’s global optimization toolbox. Then, we assess the accuracy of estimation for the trained ANNs. In this way, for the first time in the literature, we compare these methods for the optimization of an ANN. The used data sets are also available in MATLAB. Based on the acquired results, in some data sets, training with LMA, and for some others training with PSO cause the best results, however, training with LMA is faster, significantly. Although the used approaches and the obtained conclusions are beneficial for researchers that work in this field, they have some limitations. For instance, since only the functions and data sets from MATLAB are used, it can only serve as an example for researchers. |
publishDate |
2021 |
dc.date.none.fl_str_mv |
2021-07 2021-07-01T00:00:00Z 2022-01-21T15:35:33Z |
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/10400.14/36530 |
url |
http://hdl.handle.net/10400.14/36530 |
dc.language.iso.fl_str_mv |
eng |
language |
eng |
dc.relation.none.fl_str_mv |
2331-6446 10.13189/ujam.2021.090201 |
dc.rights.driver.fl_str_mv |
info:eu-repo/semantics/openAccess |
eu_rights_str_mv |
openAccess |
dc.format.none.fl_str_mv |
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_ |
1799132017776918528 |