Tuning of the structure and parameters of a neural network using an improved genetic algorithm

Author

Leung, Frank H F ; Lam, H.K. ; Ling, S.H. ; Tam, Peter K S

Author_Institution

Dept. of Electron. & Inf. Eng., Hong Kong Polytech. Univ., Kowloon, China

Volume

14

Issue

1

fYear

2003

fDate

1/1/2003 12:00:00 AM

Firstpage

79

Lastpage

88

Abstract

This paper presents the tuning of the structure and parameters of a neural network using an improved genetic algorithm (GA). It is also shown that the improved GA performs better than the standard GA based on some benchmark test functions. A neural network with switches introduced to its links is proposed. By doing this, the proposed neural network can learn both the input-output relationships of an application and the network structure using the improved GA. The number of hidden nodes is chosen manually by increasing it from a small number until the learning performance in terms of fitness value is good enough. Application examples on sunspot forecasting and associative memory are given to show the merits of the improved GA and the proposed neural network.

Keywords

content-addressable storage; genetic algorithms; learning (artificial intelligence); neural nets; performance evaluation; associative memory; benchmark test functions; fitness value; hidden nodes; improved genetic algorithm; input-output relationships; learning; learning performance; neural network parameter tuning; neural network structure; search technique; sunspot forecasting; Associative memory; Backpropagation algorithms; Benchmark testing; Fuzzy control; Genetic algorithms; Genetic mutations; Neural networks; Performance evaluation; Signal processing algorithms; Switches;

fLanguage

English

Journal_Title

Neural Networks, IEEE Transactions on

Publisher

ieee

ISSN

1045-9227

Type

jour

DOI

10.1109/TNN.2002.804317

Filename

1176129