Adjusting the parameters of radial basis function networks using Particle Swarm Optimization

Author

Esmaeili, A. ; Mozayani, N.

Author_Institution

Sch. of Comput. Eng., Iran Univ. of Sci. & Technol., Tehran

fYear

2009

fDate

11-13 May 2009

Firstpage

179

Lastpage

181

Abstract

Particle swarm optimization (PSO), a new promising evolutionary optimization technique, has a wide range of application in optimization problems including training of artificial neural networks. In this paper, an attempt is made to completely train a RBF neural network architecture including the centers, optimum spreads, and the number of hidden units. The proposed method has been evaluated on some benchmark problems: iris, wine, glass, new-thyroid and its accuracy was compared with other algorithms. The results show its strong generalization ability.

Keywords

evolutionary computation; generalisation (artificial intelligence); learning (artificial intelligence); neural net architecture; particle swarm optimisation; radial basis function networks; artificial neural network training; evolutionary optimization technique; generalization ability; neural network architecture; particle swarm optimization; radial basis function networks; Application software; Artificial neural networks; Clustering algorithms; Computational intelligence; Computer networks; Multi-layer neural network; Neural networks; Particle measurements; Particle swarm optimization; Radial basis function networks; Neural Networks; Neural Networks Training; PSO; RBF Networks;

fLanguage

English

Publisher

ieee

Conference_Titel

Computational Intelligence for Measurement Systems and Applications, 2009. CIMSA '09. IEEE International Conference on

Conference_Location

Hong Kong

Print_ISBN

978-1-4244-3819-8

Electronic_ISBN

978-1-4244-3820-4

Type

conf

DOI

10.1109/CIMSA.2009.5069942

Filename

5069942