Evolving artificial neural networks using an improved PSO and DPSO

Abstract

This paper presents an improved particle swarm optimization (PSO) and discrete PSO (DPSO) with an enhancement operation by using a self-adaptive evolution strategies (ES). This improved PSO/DPSO is proposed for joint optimization of three-layer feedforward artificial neural network (ANN) structure and parameters (weights and bias), which is named ESPNet. The experimental results on two real-world problems show that ESPNet can produce compact ANNs with good generalization ability.

DOI: 10.1016/j.neucom.2007.10.013

Extracted Key Phrases

5 Figures and Tables

0502008200920102011201220132014201520162017
Citations per Year

209 Citations

Semantic Scholar estimates that this publication has received between 97 and 399 citations based on the available data.

See our FAQ for additional information.

Cite this paper

@article{Yu2008EvolvingAN, title={Evolving artificial neural networks using an improved PSO and DPSO}, author={Jianbo Yu and Shijin Wang and Lifeng Xi}, journal={Neurocomputing}, year={2008}, volume={71}, pages={1054-1060} }