Design of beta neural systems using differential evolution

Author

Moalla, Sawsen ; Alimi, Adel M. ; Derbel, Nabil

Author_Institution

REGIM, Nat. Sch. of Eng. of Sfax, Tunisia

Volume

3

fYear

2002

fDate

6-9 Oct. 2002

Abstract

Differential evolution (DE) is an exceptionally fast and robust population based search algorithm that is able to locate near optimal solutions to difficult problems. Beside its good convergence properties, DE is very simple to understand and to implement. This paper describes an evolutionary neural network-training algorithm for beta basis function neural networks (BBFNN) using DE. Application to function approximation problems are considered to demonstrate the performance of the BBFNN and of the evolutionary algorithm.

Keywords

evolutionary computation; function approximation; learning (artificial intelligence); multilayer perceptrons; neural net architecture; radial basis function networks; search problems; beta basis function neural networks; beta neural systems design; convergence; differential evolution; evolutionary algorithm; evolutionary neural network-training algorithm; function approximation problems; near optimal solutions; performance; robust population based search algorithm; Approximation algorithms; Evolutionary computation; Function approximation; Intelligent control; Laboratories; Machine intelligence; Multi-layer neural network; Neural networks; Radial basis function networks; Robustness;

fLanguage

English

Publisher

ieee

Conference_Titel

Systems, Man and Cybernetics, 2002 IEEE International Conference on

ISSN

1062-922X

Print_ISBN

0-7803-7437-1

Type

conf

DOI

10.1109/ICSMC.2002.1176111

Filename

1176111