A consideration on the learning algorithm of neural network-utilization of the hierarchical structure stochastic automata for the backpropagation method with momentum

Author

Baba, N. ; Sato, K.

Author_Institution

Dept. of Inf. Sci., Osaka Kyoiku Univ., Ikeda, Japan

Volume

3

fYear

1998

fDate

21-23 Apr 1998

Firstpage

7

Abstract

Backpropagation (BP) method with momentum has often been applied to adapt artificial neural networks for various pattern classification problems. However, an important limitation of this method is that its learning performance depends heavily upon the selection of the values of momentum factor and step size. In this paper, it is shown that the hierarchical structure stochastic automata can be used for finding appropriate values of the parameters involved in the BP method with momentum

Keywords

backpropagation; neural nets; pattern classification; stochastic automata; backpropagation; hierarchical structure stochastic automata; learning; learning algorithm; momentum factor; neural network; pattern classification; step size; Artificial neural networks; Cities and towns; Information science; Intelligent systems; Learning automata; Learning systems; Neural networks; Pattern classification; Stochastic processes; Stochastic systems;

fLanguage

English

Publisher

ieee

Conference_Titel

Knowledge-Based Intelligent Electronic Systems, 1998. Proceedings KES '98. 1998 Second International Conference on

Conference_Location

Adelaide, SA

Print_ISBN

0-7803-4316-6

Type

conf

DOI

10.1109/KES.1998.725945

Filename

725945