Evolutionary Algorithm Based Radial Basis Function Neural Network for Function Approximation

Author

Kuo, R.J. ; Hu, Tung-Lai ; Chen, Zhen-Yao

Author_Institution

Dept. of Ind. Manage., Nat. Taiwan Univ. of Sci. & Technol., Taipei, Taiwan

fYear

2009

fDate

11-13 June 2009

Firstpage

1

Lastpage

4

Abstract

This study attempts to enhance the performance of radial basis function neural network (RBFnn) using self- organizing map neural network (SOMnn). In addition, the hybrid of genetic algorithm and particle swarm optimization (HGP) algorithm is employed to train RBFnn for function approximation. The proposed SOM-HGP evolutionary algorithm combines the automatically clustering ability of SOMnn and the HGP algorithm. Experimental results for three continuous test functions show that the algorithm has the best performance than GA [21], PSO [8], HPSGO [15] for training RBFnn.

Keywords

evolutionary computation; function approximation; genetic algorithms; learning (artificial intelligence); mathematics computing; particle swarm optimisation; pattern clustering; radial basis function networks; self-organising feature maps; RBFnn function approximation; RBFnn training; SOM-HGP evolutionary algorithm; automatical clustering ability; continuous test function; evolutionary algorithm; genetic algorithm based optimization algorithm; particle swarm optimization; radial basis function neural network; self- organizing map neural network; Approximation algorithms; Clustering algorithms; Evolutionary computation; Function approximation; Genetic algorithms; Neural networks; Organizing; Particle swarm optimization; Radial basis function networks; Testing;

fLanguage

English

Publisher

ieee

Conference_Titel

Bioinformatics and Biomedical Engineering , 2009. ICBBE 2009. 3rd International Conference on

Conference_Location

Beijing

Print_ISBN

978-1-4244-2901-1

Electronic_ISBN

978-1-4244-2902-8

Type

conf

DOI

10.1109/ICBBE.2009.5162810

Filename

5162810