Differential evolution based particle swarm optimizer for neural network learning

Author

Ning, Dongfang ; Zhang, Weiguo ; Bin Li

Author_Institution

Coll. of Autom., Northwestern Polytech. Univ., Xi´´an

fYear

2008

fDate

25-27 June 2008

Firstpage

4444

Lastpage

4447

Abstract

An improved particle swarm optimizer based on differential evolution theory is proposed. This algorithm introduces differential mutation operator into the basic particle swarm optimizer in order to solve the premature convergence problem. And this new algorithm was used to training weights and thresholds of feedforward neural network, simulation results show that this approach is effective and has an excellent convergence performance.

Keywords

convergence; feedforward neural nets; learning (artificial intelligence); particle swarm optimisation; convergence; differential evolution; differential mutation operator; feedforward neural network; neural network learning; particle swarm optimizer; Artificial neural networks; Automation; Convergence; Educational institutions; Evolutionary computation; Feedforward neural networks; Genetic mutations; Intelligent control; Neural networks; Particle swarm optimization; Artificial neural network; Differential evolution; Particle swarm optimizer; Swarm intelligence;

fLanguage

English

Publisher

ieee

Conference_Titel

Intelligent Control and Automation, 2008. WCICA 2008. 7th World Congress on

Conference_Location

Chongqing

Print_ISBN

978-1-4244-2113-8

Electronic_ISBN

978-1-4244-2114-5

Type

conf

DOI

10.1109/WCICA.2008.4594525

Filename

4594525