%0 Conference Proceedings
%4 sid.inpe.br/sibgrapi/2016/09.06.21.12
%2 sid.inpe.br/sibgrapi/2016/09.06.21.12.38
%T Ajuste fino de parâmetros de Redes Neurais por Convolução utilizando o Algoritmo de Otimização das Aves Migratórias
%D 2016
%A Benato, Bárbara Caroline,
%A Papa, João Paulo,
%A Marana, Aparecido Nilceu,
%@affiliation Sao Paulo State University
%@affiliation Sao Paulo State University
%@affiliation Sao Paulo State University
%E Aliaga, Daniel G.,
%E Davis, Larry S.,
%E Farias, Ricardo C.,
%E Fernandes, Leandro A. F.,
%E Gibson, Stuart J.,
%E Giraldi, Gilson A.,
%E Gois, João Paulo,
%E Maciel, Anderson,
%E Menotti, David,
%E Miranda, Paulo A. V.,
%E Musse, Soraia,
%E Namikawa, Laercio,
%E Pamplona, Mauricio,
%E Papa, João Paulo,
%E Santos, Jefersson dos,
%E Schwartz, William Robson,
%E Thomaz, Carlos E.,
%B Conference on Graphics, Patterns and Images, 29 (SIBGRAPI)
%C São José dos Campos, SP, Brazil
%8 4-7 Oct. 2016
%I Sociedade Brasileira de Computação
%J Porto Alegre
%S Proceedings
%K aprendizado em profundidade, otimização meta-heurística.
%X The problem of fine-tuning parameters in deep learning techniques has been considerably focused in the last years, since to hand-tune them is painful and prone to errors. In this work, we introduced the Migrating Birds Optimization (MBO) to fine-tune parameters of Convolutional Neural Networks (CNNs) and Deep Belief Networks (DBNs), being the results compared against two other state-of-the-art meta-heuristic techniques. The experiments showed MBO obtained very good results in both CNNs and DBNs, but at the price of a high computational burden.
%@language pt
%3 paperBarbara_final.pdf