A genetic algorithm approach used to generate the neural network structures

Author

Liu, Zhijun ; Sugisaka, Masanori

Author_Institution

Dept. of Electr. & Electron. Eng., Oita Univ., Japan

Volume

2

fYear

1999

fDate

1999

Firstpage

763

Abstract

A genetic algorithm (GA) is implemented to search for the optimal structures of neural networks which are used for approximating a given nonlinear function. Two kinds of neural networks, i.e. the multilayer feedforward and time delay neural networks are involved in the paper. The weights of each neural network in each generation are obtained by associated training algorithms. The simulation results of nonlinear function approximation are given and some improvements in the future are outlined

Keywords

feedforward neural nets; function approximation; genetic algorithms; learning (artificial intelligence); multilayer perceptrons; neural net architecture; nonlinear functions; search problems; multilayer feedforward network; nonlinear function approximation; optimal structures; time delay neural networks; training algorithms; Artificial neural networks; Biological cells; Delay effects; Encoding; Function approximation; Genetic algorithms; Genetic engineering; Multi-layer neural network; Neural networks; Neurons;

fLanguage

English

Publisher

ieee

Conference_Titel

Intelligent Robots and Systems, 1999. IROS '99. Proceedings. 1999 IEEE/RSJ International Conference on

Conference_Location

Kyongju

Print_ISBN

0-7803-5184-3

Type

conf

DOI

10.1109/IROS.1999.812772

Filename

812772