Summary
International Symposium on Nonlinear Theory and its Applications
2005
Session Number:1-2-3
Session:
Number:1-2-3-4
Learning Ability of Evolving Affordable Neural Networks with Genetic Algorithm
Yoko Uwate, Yoshifumi Nishio,
pp.242-245
Publication Date:2005/10/18
Online ISSN:2188-5079
DOI:10.34385/proc.40.1-2-3-4
PDF download (111.7KB)
Summary:
In our previous research, we have proposed new network structure with affordable neurons in hidden layer of the feedforward neural network to reflect real brain mechanism. We named this proposed network "Affordable Neural Network." We consider that operation of affordable neurons are especially effective on evolution of neural network in brain. In this study, we investigate the performance of affordable neural network when the hidden layer is evolved using Genetic Algorithm. By computer simulations, we consider that the affordable neurons exert an important influence on evolution process in the hidden layer of the network.