A multi-population cooperative particle swarm optimizer for neural network training

Authors:
Ben Niu;Yun-Long Zhu;Xiao-Xian He
Affiliations:
Shenyang Institute of Automation, Chinese Academy of Sciences, Shenyang, China;Shenyang Institute of Automation, Chinese Academy of Sciences, Shenyang, China;Shenyang Institute of Automation, Chinese Academy of Sciences, Shenyang, China
Venue:
ISNN'06 Proceedings of the Third international conference on Advances in Neural Networks - Volume Part I
Year:
2006

Citing 7
Cited 2

Radial basis function network configuration using genetic algorithms

Neural Networks
Swarm intelligence

Swarm intelligence
Evolutionary Optimization Versus Particle Swarm Optimization: Philosophy and Performance Differences

EP '98 Proceedings of the 7th International Conference on Evolutionary Programming VII
Multi-population cooperative particle swarm optimization

ECAL'05 Proceedings of the 8th European conference on Advances in Artificial Life
Construction of fuzzy models for dynamic systems using multi-population cooperative particle swarm optimizer

FSKD'05 Proceedings of the Second international conference on Fuzzy Systems and Knowledge Discovery - Volume Part I
The particle swarm - explosion, stability, and convergence in amultidimensional complex space

IEEE Transactions on Evolutionary Computation
Back-propagation network and its configuration for blood vessel detection in angiograms

IEEE Transactions on Neural Networks

Symbiotic multi-swarm PSO for portfolio optimization

ICIC'09 Proceedings of the Intelligent computing 5th international conference on Emerging intelligent computing technology and applications
Information entropy and interaction optimization model based on swarm intelligence

ICNC'06 Proceedings of the Second international conference on Advances in Natural Computation - Volume Part II

Quantified Score

Hi-index	0.00

Visualization

Abstract

This paper presents a new learning algorithm, Multi-Population Cooperative Particle Swarm Optimizer (MCPSO), for neural network training. MCPSO is based on a master-slave model, in which a population consists of a master group and several slave groups. The slave groups execute a single PSO or its variants independently to maintain the diversity of particles, while the master group evolves based on its own information and also the information of the slave groups. The particles both in the master group and the slave groups are co-evolved during the search process by employing a parameter, termed migration factor. The MCPSO is applied for training a multilayer feed-forward neural network, for three benchmark classification problems. The performance of MCPSO used for neural network training is compared to that of Back Propagation (BP), genetic algorithm (GA) and standard PSO (SPSO), demonstrating its effectiveness and efficiency.