κ-Entropy Based Restricted Boltzmann Machines

Registro completo de metadados
MetadadosDescriçãoIdioma
Autor(es): dc.contributorUniversidade Federal de São Carlos (UFSCar)-
Autor(es): dc.contributorUniversidade Estadual Paulista (Unesp)-
Autor(es): dc.creatorPassos, Leandro Aparecido-
Autor(es): dc.creatorCleison Santana, Marcos [UNESP]-
Autor(es): dc.creatorMoreira, Thierry [UNESP]-
Autor(es): dc.creatorPapa, Joao Paulo [UNESP]-
Data de aceite: dc.date.accessioned2022-02-22T00:32:56Z-
Data de disponibilização: dc.date.available2022-02-22T00:32:56Z-
Data de envio: dc.date.issued2020-12-11-
Data de envio: dc.date.issued2020-12-11-
Data de envio: dc.date.issued2019-07-01-
Fonte completa do material: dc.identifierhttp://dx.doi.org/10.1109/IJCNN.2019.8851714-
Fonte completa do material: dc.identifierhttp://hdl.handle.net/11449/201217-
Fonte: dc.identifier.urihttp://educapes.capes.gov.br/handle/11449/201217-
Descrição: dc.descriptionRestricted 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.-
Descrição: dc.descriptionDepartment of Computing UFSCar - Federal University of São Carlos-
Descrição: dc.descriptionSchool of Sciences UNESP - São Paulo State University-
Descrição: dc.descriptionSchool of Sciences UNESP - São Paulo State University-
Idioma: dc.languageen-
Relação: dc.relationProceedings of the International Joint Conference on Neural Networks-
???dc.source???: dc.sourceScopus-
Palavras-chave: dc.subjectKaniadakis Entropy-
Palavras-chave: dc.subjectMachine Learning-
Palavras-chave: dc.subjectRestricted Boltzmann Machines-
Título: dc.titleκ-Entropy Based Restricted Boltzmann Machines-
Aparece nas coleções:Repositório Institucional - Unesp

Não existem arquivos associados a este item.