kappa-Entropy Based Restricted Boltzmann Machines

Autor(es)

Passos, Leandro Aparecido ; Santana, Marcos Cleison ; Moreira, Thierry ; Papa, Joao Paulo ; IEEE

• Tipo de documento: Artigo Científico
• Fonte: 2019 INTERNATIONAL JOINT CONFERENCE ON NEURAL NETWORKS (IJCNN); v. N/A, p. 8-pg., 2019-01-01.

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. (AU)

• Processo FAPESP: 13/07375-0 - CeMEAI - Centro de Ciências Matemáticas Aplicadas à Indústria
• Beneficiário: Francisco Louzada Neto
• Modalidade de apoio: Auxílio à Pesquisa - Centros de Pesquisa, Inovação e Difusão - CEPIDs
• Processo FAPESP: 14/12236-1 - AnImaLS: Anotação de Imagem em Larga Escala: o que máquinas e especialistas podem aprender interagindo?
• Beneficiário: Alexandre Xavier Falcão
• Modalidade de apoio: Auxílio à Pesquisa - Temático
• Processo FAPESP: 16/06441-7 - Recuperação de informação semântica em grandes bases de vídeos
• Beneficiário: Jurandy Gomes de Almeida Junior
• Modalidade de apoio: Auxílio à Pesquisa - Regular