Energy-Based Dropout in Restricted Boltzmann Machines: Why Not Go Random

Registro completo de metadados
MetadadosDescriçãoIdioma
Autor(es): dc.contributorUniversidade Estadual Paulista (Unesp)-
Autor(es): dc.creatorRoder, Mateus-
Autor(es): dc.creatorde Rosa, Gustavo Henrique-
Autor(es): dc.creatorde Albuquerque, Victor Hugo C.-
Autor(es): dc.creatorRossi, Andre L. D.-
Autor(es): dc.creatorPapa, Joao P.-
Data de aceite: dc.date.accessioned2022-02-22T00:44:58Z-
Data de disponibilização: dc.date.available2022-02-22T00:44:58Z-
Data de envio: dc.date.issued2021-06-25-
Data de envio: dc.date.issued2021-06-25-
Data de envio: dc.date.issued2019-12-31-
Fonte completa do material: dc.identifierhttp://dx.doi.org/10.1109/TETCI.2020.3043764-
Fonte completa do material: dc.identifierhttp://hdl.handle.net/11449/205676-
Fonte: dc.identifier.urihttp://educapes.capes.gov.br/handle/11449/205676-
Descrição: dc.descriptionDeep learning architectures have been widely fostered throughout the last years, being used in a wide range of applications, such as object recognition, image reconstruction, and signal processing. Nevertheless, such models suffer from a common problem known as overfitting, which limits the network from predicting unseen data effectively. Regularization approaches arise in an attempt to address such a shortcoming. Among them, one can refer to the well-known Dropout, which tackles the problem by randomly shutting down a set of neurons and their connections according to a certain probability. Therefore, this approach does not consider any additional knowledge to decide which units should be disconnected. In this paper, we propose an energy-based Dropout (E-Dropout) that makes conscious decisions whether a neuron should be dropped or not. Specifically, we design this regularization method by correlating neurons and the model’s energy as an importance level for further applying it to energy-based models, such as Restricted Boltzmann Machines (RBMs). The experimental results over several benchmark datasets revealed the proposed approach’s suitability compared to the traditional Dropout and the standard RBMs.-
Descrição: dc.descriptionSão Paulo State University, Sao Paulo, SP 17033360 Brazil (e-mail: mateus.roder@unesp.br).-
Descrição: dc.descriptionSão Paulo State University, Sao Paulo, SP 17033360 Brazil (e-mail: gustavo.rosa@unesp.br).-
Descrição: dc.descriptionARMTEC Tecnologia em Robótica, Fortaleza, /CE 60150000 Brazil (e-mail: victor.albuquerque@ieee.org).-
Descrição: dc.descriptionSão Paulo State University, Sao Paulo, SP 17033360 Brazil (e-mail: andre.rossi@unesp.br).-
Descrição: dc.descriptionSão Paulo State University, Sao Paulo, SP 17033360 Brazil (e-mail: joao.papa@unesp.br).-
Idioma: dc.languageen-
Relação: dc.relationIEEE Transactions on Emerging Topics in Computational Intelligence-
???dc.source???: dc.sourceScopus-
Palavras-chave: dc.subjectComputational modeling-
Palavras-chave: dc.subjectDropout-
Palavras-chave: dc.subjectenergy-based dropout-
Palavras-chave: dc.subjectImage reconstruction-
Palavras-chave: dc.subjectmachine learning-
Palavras-chave: dc.subjectMathematical model-
Palavras-chave: dc.subjectNeurons-
Palavras-chave: dc.subjectregularization-
Palavras-chave: dc.subjectrestricted boltzmann machines-
Palavras-chave: dc.subjectStandards-
Palavras-chave: dc.subjectTask analysis-
Palavras-chave: dc.subjectTraining-
Título: dc.titleEnergy-Based Dropout in Restricted Boltzmann Machines: Why Not Go Random-
Tipo de arquivo: dc.typelivro digital-
Aparece nas coleções:Repositório Institucional - Unesp

Não existem arquivos associados a este item.