Summary
International Symposium on Nonlinear Theory and its Applications
2008
Session Number:C4L-E
Session:
Number:C4L-E2
A Learning Algorithm of Binary Neural Networks Based on Real-Coded GA
Yu Akedo , Hidehiro Nakano, Arata Miyauchi,
pp.-
Publication Date:2008/9/7
Online ISSN:2188-5079
DOI:10.34385/proc.42.C4L-E2
PDF download (275.9KB)
Summary:
In this paper, we propose a learning algorithm of Binary Neural Networks (BNNs) based on real-coded genetic algorithm. The algorithm encodes parameters of hidden layer neurons as individuals consisting of real number vectors. The proposed algorithm can reduce the number of hidden layer neurons and has high recognition performance, comparing with the conventional algorithm. Through basic numerical experiments, we verify these advantages.