An improved particle swarm optimization for evolving feedforward artificial neural networks

• Published in: Neural processing letters Vol. 26; no. 3; pp. 217 - 231
• Main Authors: Yu, Jianbo, Xi, Lifeng, Wang, Shijin
• Format: Journal Article
• Language: English
• Published: Dordrecht Springer 01.12.2007; Springer Nature B.V
• Subjects: Algorithms; Applied sciences; Artificial intelligence; Artificial neural networks; Computer science; control theory; systems; Connectionism. Neural networks; Exact sciences and technology; Particle swarm optimization; Performance enhancement; Automation; Evolutionary algorithm; Particle swarm optimization, Generalization; Swarm intelligence; Neural network; Feedforward; Search algorithm; Artificial neural network, Evolutionary algorithm
• ISSN: 1370-4621; 1573-773X
• DOI: 10.1007/s11063-007-9053-x

This paper presents a new evolutionary artificial neural network (ANN) algorithm named IPSONet that is based on an improved particle swarm optimization (PSO). The improved PSO employs parameter automation strategy, velocity resetting, and crossover and mutations to significantly improve the performance of the original PSO algorithm in global search and fine-tuning of the solutions. IPSONet uses the improved PSO to address the design problem of feedforward ANN. Unlike most previous studies on only using PSO to evolve weights of ANNs, this study puts its emphasis on using the improved PSO to evolve simultaneously structure and weights of ANNs by a specific individual representation and evolutionary scheme. The performance of IPSONet has been evaluated on several benchmarks. The results demonstrate that IPSONet can produce compact ANNs with good generalization ability.