The Optimization of Nonlinear Systems Identification Based on Genetic Algorithms

Author

Tan, Xin ; Yang, Huaqian

Author_Institution

Inst. of Commun., Chongqing Univ. of Posts & Telecommun.

Volume

1

fYear

2006

fDate

Nov. 2006

Firstpage

266

Lastpage

269

Abstract

Gaussian-Hopfield neural networks (GHNNs) are widely used in identifying nonlinear systems, however, the delta-learning rule is easy to encounter the local minima problem. In this paper, genetic algorithms are adopted to overcome the problem. The proposed method is used to improve the speed of searching for a set of optimal parameters for the GHNNs. To verify the validity of the proposed method, simulation experiments are provided. The results have been shown that the ability of the proposed method to identify nonlinear systems is satisfactory

Keywords

Gaussian processes; Hopfield neural nets; genetic algorithms; learning (artificial intelligence); nonlinear systems; simulation; Gaussian-Hopfield neural network; delta-learning rule; genetic algorithm; nonlinear system identification; simulation; Computer science education; Delay effects; Educational institutions; Educational technology; Gaussian processes; Genetic algorithms; History; Neural networks; Nonlinear systems; Telecommunication computing;

fLanguage

English

Publisher

ieee

Conference_Titel

Computational Intelligence and Security, 2006 International Conference on

Conference_Location

Guangzhou

Print_ISBN

1-4244-0605-6

Electronic_ISBN

1-4244-0605-6

Type

conf

DOI

10.1109/ICCIAS.2006.294134

Filename

4072087