Using evolutionary programming to construct Hopfield neural networks

Author

Xiangwu, Meng ; Hu, Cheng

Author_Institution

Inst. of Software, Acad. Sinica, Beijing, China

Volume

1

fYear

1997

fDate

28-31 Oct 1997

Firstpage

571

Abstract

This paper presents a new method for constructing discrete-time Hopfield neural networks using evolutionary programming. Under constraints of fixed points, limit cycles or iteration sequences, the method simultaneously acquires both the topology and weights for Hopfield neural networks by solving inequalities. It copes with the limitations of the canonical Hopfield learning algorithm. Experimental results are presented which clearly demonstrate the effectiveness of our approach

Keywords

Hopfield neural nets; discrete time systems; genetic algorithms; iterative methods; learning (artificial intelligence); limit cycles; network topology; sequences; canonical Hopfield learning algorithm; constraints; discrete-time Hopfield neural networks; evolutionary programming; fixed points; inequalities; iteration sequences; limit cycles; network topology; node weights; Artificial neural networks; Automatic control; Control systems; Genetic programming; Hopfield neural networks; Limit-cycles; Network topology; Neural networks; Neurons; Pattern recognition;

fLanguage

English

Publisher

ieee

Conference_Titel

Intelligent Processing Systems, 1997. ICIPS '97. 1997 IEEE International Conference on

Conference_Location

Beijing

Print_ISBN

0-7803-4253-4

Type

conf

DOI

10.1109/ICIPS.1997.672848

Filename

672848