Multilayer Perceptron Networks Training Using Particle Swarm Optimization with Minimum Velocity Constraints

Authors:
Xiaorong Pu;Zhongjie Fang;Yongguo Liu
Affiliations:
Computational Intelligence Laboratory, School of Computer Science & Engineering, University of Electronic Science & Technology of China, Chengdu 610054, P.R. China;Computational Intelligence Laboratory, School of Computer Science & Engineering, University of Electronic Science & Technology of China, Chengdu 610054, P.R. China;Computational Intelligence Laboratory, School of Computer Science & Engineering, University of Electronic Science & Technology of China, Chengdu 610054, P.R. China
Venue:
ISNN '07 Proceedings of the 4th international symposium on Neural Networks: Advances in Neural Networks, Part III
Year:
2007

Citing 5
Cited 1

Multilayer feedforward networks are universal approximators

Neural Networks
First- and second-order methods for learning: between steepest descent and Newton's method

Neural Computation
Neural Networks: A Comprehensive Foundation

Neural Networks: A Comprehensive Foundation
Using the particle swarm optimization technique to train a recurrent neural model

ICTAI '97 Proceedings of the 9th International Conference on Tools with Artificial Intelligence
Fuzzy Adaptive Turbulent Particle Swarm Optimization

HIS '05 Proceedings of the Fifth International Conference on Hybrid Intelligent Systems

Training neural networks using Central Force Optimization and Particle Swarm Optimization: Insights and comparisons

Expert Systems with Applications: An International Journal

Quantified Score

Hi-index	0.00

Visualization

Abstract

Multilayer perceptron networks have been successfully trai- ned by error backpropagation algorithm. We show that Particle Swarm Optimization(PSO) with minimum velocity constraints can efficiently be applied to train multilayer perceptrons to overcome premature convergence and alleviates the influence of dimensionality increasing. The experiments of two multilayer perceptrons trained by PSO with minimum velocity constraints are carried out. The result clearly demonstrate the improvement of the proposed algorithm over the standard PSO in terms of convergence.