kappa-Entropy Based Restricted Boltzmann Machines
Autor(a) principal: | |
---|---|
Data de Publicação: | 2019 |
Outros Autores: | , , , |
Tipo de documento: | Artigo de conferência |
Idioma: | eng |
Título da fonte: | Repositório Institucional da UNESP |
Texto Completo: | http://hdl.handle.net/11449/197766 |
Resumo: | Restricted Boltzmann Machines achieved notorious popularity in the scientific community in the last decade due to outstanding results in a wide range of applications and also for providing the required mechanisms to build successful deep learning models, i.e., Deep Belief Networks and Deep Boltzmann Machines. However, their main bottleneck is related to the learning step, which is usually time-consuming. In this paper, we introduce a Sigmoid-like family of functions based on the Kaniadakis entropy formulation in the context of the RBM learning procedure. Experiments concerning binary image reconstruction are conducted in four public datasets to evaluate the robustness of the proposed approach. The results suggest that such a family of functions is suitable to increase the convergence rate when compared to standard functions employed by the research community. |
id |
UNSP_0727ba45b1df306c71457b2ace0955bc |
---|---|
oai_identifier_str |
oai:repositorio.unesp.br:11449/197766 |
network_acronym_str |
UNSP |
network_name_str |
Repositório Institucional da UNESP |
repository_id_str |
2946 |
spelling |
kappa-Entropy Based Restricted Boltzmann MachinesRestricted Boltzmann MachinesKaniadakis EntropyMachine LearningRestricted Boltzmann Machines achieved notorious popularity in the scientific community in the last decade due to outstanding results in a wide range of applications and also for providing the required mechanisms to build successful deep learning models, i.e., Deep Belief Networks and Deep Boltzmann Machines. However, their main bottleneck is related to the learning step, which is usually time-consuming. In this paper, we introduce a Sigmoid-like family of functions based on the Kaniadakis entropy formulation in the context of the RBM learning procedure. Experiments concerning binary image reconstruction are conducted in four public datasets to evaluate the robustness of the proposed approach. The results suggest that such a family of functions is suitable to increase the convergence rate when compared to standard functions employed by the research community.Coordenação de Aperfeiçoamento de Pessoal de Nível Superior (CAPES)Fundação de Amparo à Pesquisa do Estado de São Paulo (FAPESP)Conselho Nacional de Desenvolvimento Científico e Tecnológico (CNPq)UFSCar Fed Univ Sao Carlos, Dept Comp, Sao Carlos, SP, BrazilUNESP Sao Paulo State Univ, Sch Sci, Bauru, SP, BrazilUNESP Sao Paulo State Univ, Sch Sci, Bauru, SP, BrazilCAPES: 001FAPESP: 2013/07375-0FAPESP: 2014/12236-1FAPESP: 2016/06441-7CNPq: 307066/2017-7IeeeUniversidade Federal de São Carlos (UFSCar)Universidade Estadual Paulista (Unesp)Passos, Leandro AparecidoSantana, Marcos Cleison [UNESP]Moreira, Thierry [UNESP]Papa, Joao Paulo [UNESP]IEEE2020-12-11T17:02:09Z2020-12-11T17:02:09Z2019-01-01info:eu-repo/semantics/publishedVersioninfo:eu-repo/semantics/conferenceObject82019 International Joint Conference On Neural Networks (ijcnn). New York: Ieee, 8 p., 2019.2161-4393http://hdl.handle.net/11449/197766WOS:000530893800033Web of Sciencereponame:Repositório Institucional da UNESPinstname:Universidade Estadual Paulista (UNESP)instacron:UNESPeng2019 International Joint Conference On Neural Networks (ijcnn)info:eu-repo/semantics/openAccess2024-04-23T16:11:34Zoai:repositorio.unesp.br:11449/197766Repositório InstitucionalPUBhttp://repositorio.unesp.br/oai/requestopendoar:29462024-04-23T16:11:34Repositório Institucional da UNESP - Universidade Estadual Paulista (UNESP)false |
dc.title.none.fl_str_mv |
kappa-Entropy Based Restricted Boltzmann Machines |
title |
kappa-Entropy Based Restricted Boltzmann Machines |
spellingShingle |
kappa-Entropy Based Restricted Boltzmann Machines Passos, Leandro Aparecido Restricted Boltzmann Machines Kaniadakis Entropy Machine Learning |
title_short |
kappa-Entropy Based Restricted Boltzmann Machines |
title_full |
kappa-Entropy Based Restricted Boltzmann Machines |
title_fullStr |
kappa-Entropy Based Restricted Boltzmann Machines |
title_full_unstemmed |
kappa-Entropy Based Restricted Boltzmann Machines |
title_sort |
kappa-Entropy Based Restricted Boltzmann Machines |
author |
Passos, Leandro Aparecido |
author_facet |
Passos, Leandro Aparecido Santana, Marcos Cleison [UNESP] Moreira, Thierry [UNESP] Papa, Joao Paulo [UNESP] IEEE |
author_role |
author |
author2 |
Santana, Marcos Cleison [UNESP] Moreira, Thierry [UNESP] Papa, Joao Paulo [UNESP] IEEE |
author2_role |
author author author author |
dc.contributor.none.fl_str_mv |
Universidade Federal de São Carlos (UFSCar) Universidade Estadual Paulista (Unesp) |
dc.contributor.author.fl_str_mv |
Passos, Leandro Aparecido Santana, Marcos Cleison [UNESP] Moreira, Thierry [UNESP] Papa, Joao Paulo [UNESP] IEEE |
dc.subject.por.fl_str_mv |
Restricted Boltzmann Machines Kaniadakis Entropy Machine Learning |
topic |
Restricted Boltzmann Machines Kaniadakis Entropy Machine Learning |
description |
Restricted Boltzmann Machines achieved notorious popularity in the scientific community in the last decade due to outstanding results in a wide range of applications and also for providing the required mechanisms to build successful deep learning models, i.e., Deep Belief Networks and Deep Boltzmann Machines. However, their main bottleneck is related to the learning step, which is usually time-consuming. In this paper, we introduce a Sigmoid-like family of functions based on the Kaniadakis entropy formulation in the context of the RBM learning procedure. Experiments concerning binary image reconstruction are conducted in four public datasets to evaluate the robustness of the proposed approach. The results suggest that such a family of functions is suitable to increase the convergence rate when compared to standard functions employed by the research community. |
publishDate |
2019 |
dc.date.none.fl_str_mv |
2019-01-01 2020-12-11T17:02:09Z 2020-12-11T17:02:09Z |
dc.type.status.fl_str_mv |
info:eu-repo/semantics/publishedVersion |
dc.type.driver.fl_str_mv |
info:eu-repo/semantics/conferenceObject |
format |
conferenceObject |
status_str |
publishedVersion |
dc.identifier.uri.fl_str_mv |
2019 International Joint Conference On Neural Networks (ijcnn). New York: Ieee, 8 p., 2019. 2161-4393 http://hdl.handle.net/11449/197766 WOS:000530893800033 |
identifier_str_mv |
2019 International Joint Conference On Neural Networks (ijcnn). New York: Ieee, 8 p., 2019. 2161-4393 WOS:000530893800033 |
url |
http://hdl.handle.net/11449/197766 |
dc.language.iso.fl_str_mv |
eng |
language |
eng |
dc.relation.none.fl_str_mv |
2019 International Joint Conference On Neural Networks (ijcnn) |
dc.rights.driver.fl_str_mv |
info:eu-repo/semantics/openAccess |
eu_rights_str_mv |
openAccess |
dc.format.none.fl_str_mv |
8 |
dc.publisher.none.fl_str_mv |
Ieee |
publisher.none.fl_str_mv |
Ieee |
dc.source.none.fl_str_mv |
Web of Science 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_ |
1799965744069345280 |