Using metalearning for parameter tuning in neural networks
Autor(a) principal: | |
---|---|
Data de Publicação: | 2018 |
Outros Autores: | , , |
Tipo de documento: | Artigo |
Idioma: | eng |
Título da fonte: | Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos) |
Texto Completo: | http://repositorio.inesctec.pt/handle/123456789/7008 http://dx.doi.org/10.1007/978-3-319-68195-5_120 |
Resumo: | Neural networks have been applied as a machine learning tool in many different areas. Recently, they have gained increased attention with what is now called deep learning. Neural networks algorithms have several parameters that need to be tuned in order to maximize performance. The definition of these parameters can be a difficult, extensive and time consuming task, even for expert users. One approach that has been successfully used for algorithm and parameter selection is metalearning. Metalearning consists in using machine learning algorithm on (meta)data from machine learning experiments to map the characteristics of the data with the performance of the algorithms. In this paper we study how a metalearning approach can be used to obtain a good set of parameters to learn a neural network for a given new dataset. Our results indicate that with metalearning we can successfully learn classifiers from past learning tasks that are able to define appropriate parameters. © 2018, Springer International Publishing AG. |
id |
RCAP_99d6ef35da10f8013973e0f2ba65d797 |
---|---|
oai_identifier_str |
oai:repositorio.inesctec.pt:123456789/7008 |
network_acronym_str |
RCAP |
network_name_str |
Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos) |
repository_id_str |
7160 |
spelling |
Using metalearning for parameter tuning in neural networksNeural networks have been applied as a machine learning tool in many different areas. Recently, they have gained increased attention with what is now called deep learning. Neural networks algorithms have several parameters that need to be tuned in order to maximize performance. The definition of these parameters can be a difficult, extensive and time consuming task, even for expert users. One approach that has been successfully used for algorithm and parameter selection is metalearning. Metalearning consists in using machine learning algorithm on (meta)data from machine learning experiments to map the characteristics of the data with the performance of the algorithms. In this paper we study how a metalearning approach can be used to obtain a good set of parameters to learn a neural network for a given new dataset. Our results indicate that with metalearning we can successfully learn classifiers from past learning tasks that are able to define appropriate parameters. © 2018, Springer International Publishing AG.2018-01-18T23:36:33Z2018-01-01T00:00:00Z2018info:eu-repo/semantics/publishedVersioninfo:eu-repo/semantics/articleapplication/pdfhttp://repositorio.inesctec.pt/handle/123456789/7008http://dx.doi.org/10.1007/978-3-319-68195-5_120engCatarina Félix OliveiraCarlos Manuel SoaresAlípio JorgeHugo Miguel Ferreirainfo: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:RCAAP2023-05-15T10:20:21Zoai:repositorio.inesctec.pt:123456789/7008Portal AgregadorONGhttps://www.rcaap.pt/oai/openaireopendoar:71602024-03-19T17:53:00.444730Repositório 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 |
Using metalearning for parameter tuning in neural networks |
title |
Using metalearning for parameter tuning in neural networks |
spellingShingle |
Using metalearning for parameter tuning in neural networks Catarina Félix Oliveira |
title_short |
Using metalearning for parameter tuning in neural networks |
title_full |
Using metalearning for parameter tuning in neural networks |
title_fullStr |
Using metalearning for parameter tuning in neural networks |
title_full_unstemmed |
Using metalearning for parameter tuning in neural networks |
title_sort |
Using metalearning for parameter tuning in neural networks |
author |
Catarina Félix Oliveira |
author_facet |
Catarina Félix Oliveira Carlos Manuel Soares Alípio Jorge Hugo Miguel Ferreira |
author_role |
author |
author2 |
Carlos Manuel Soares Alípio Jorge Hugo Miguel Ferreira |
author2_role |
author author author |
dc.contributor.author.fl_str_mv |
Catarina Félix Oliveira Carlos Manuel Soares Alípio Jorge Hugo Miguel Ferreira |
description |
Neural networks have been applied as a machine learning tool in many different areas. Recently, they have gained increased attention with what is now called deep learning. Neural networks algorithms have several parameters that need to be tuned in order to maximize performance. The definition of these parameters can be a difficult, extensive and time consuming task, even for expert users. One approach that has been successfully used for algorithm and parameter selection is metalearning. Metalearning consists in using machine learning algorithm on (meta)data from machine learning experiments to map the characteristics of the data with the performance of the algorithms. In this paper we study how a metalearning approach can be used to obtain a good set of parameters to learn a neural network for a given new dataset. Our results indicate that with metalearning we can successfully learn classifiers from past learning tasks that are able to define appropriate parameters. © 2018, Springer International Publishing AG. |
publishDate |
2018 |
dc.date.none.fl_str_mv |
2018-01-18T23:36:33Z 2018-01-01T00:00:00Z 2018 |
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://repositorio.inesctec.pt/handle/123456789/7008 http://dx.doi.org/10.1007/978-3-319-68195-5_120 |
url |
http://repositorio.inesctec.pt/handle/123456789/7008 http://dx.doi.org/10.1007/978-3-319-68195-5_120 |
dc.language.iso.fl_str_mv |
eng |
language |
eng |
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_ |
1799131605447475201 |