Atlantis Press Paper Details: The Development of Neural Network Models by Revised Particle Swarm Optimization

A novel training paradigm for artificial neural networks had been developed and presented in this article. In the proposed approach, a revised version of particle swarm optimization (PSO) had been employed to find out the optimal connection weights of feed-forward artificial neural networks for given training sets. Literatures reported that conventional particle swarm optimization could easily get stuck at local optima, especially in problem domains with high dimensionality. In our scheme, a re-seeding mechanism will be invoked when the system is under the risk of converging to pre-mature solutions. The incorporation of the concept of mutation had endowed the systems with better capability in escaping local optima and approaching to the global optimum. A series of experiments were conducted to verify the feasibility and effectiveness of the proposed approach, and optimistic results were obtained as expected. In additions, the impact and influence of different parameter settings on system performance was investigated through comprehensive empirical study, as reported in this paper.

		back to author index

title:		The Development of Neural Network Models by Revised Particle Swarm Optimization
publication:		JCIS-2006 Proceedings
part of series:		Advances in Intelligent Systems Research
ISBN:		978-90-78677-01-7
ISSN:		1951-6851
DOI:		doi:10.2991/jcis.2006.138 (how to use a DOI)
author(s):		Peitsang Wu, Chin-Shiuh Shieh, Jar-Her Kao
corresponding author:		Peitsang Wu
publication date:		October 2006
keywords:		neural networks, particle swarm optimization (PSO), mutation, re-seeding.
abstract:		A novel training paradigm for artificial neural networks had been developed and presented in this article. In the proposed approach, a revised version of particle swarm optimization (PSO) had been employed to find out the optimal connection weights of feed-forward artificial neural networks for given training sets. Literatures reported that conventional particle swarm optimization could easily get stuck at local optima, especially in problem domains with high dimensionality. In our scheme, a re-seeding mechanism will be invoked when the system is under the risk of converging to pre-mature solutions. The incorporation of the concept of mutation had endowed the systems with better capability in escaping local optima and approaching to the global optimum. A series of experiments were conducted to verify the feasibility and effectiveness of the proposed approach, and optimistic results were obtained as expected. In additions, the impact and influence of different parameter settings on system performance was investigated through comprehensive empirical study, as reported in this paper.
copyright:		© Atlantis Press. This article is distributed under the terms of the Creative Commons Attribution License, which permits non-commercial use, distribution and reproduction in any medium, provided the original work is properly cited.
full text:		JCIS06-CIEF-170.pdf (77 K)