View Item 

A new particle swarm optimization algorithm for neural network optimization

Access Status
Open access
Authors
Ling, S.
Nguyen, H.
Chan, Kit Yan
Date
2009
Collection
Type
Conference Paper
Metadata
Show full item record
Abstract

This paper presents a new particle swarm optimization (PSO) algorithm for tuning parameters (weights) of neural networks. The new PSO algorithm is called fuzzy logic-based particle swarm optimization with cross-mutated operation (FPSOCM), where the fuzzy inference system is applied to determine the inertia weight of PSO and the control parameter of the proposed cross-mutated operation by using human knowledge. By introducing the fuzzy system, the value of the inertia weight becomes variable. The cross-mutated operation is effectively force the solution to escape the local optimum. Tuning parameters (weights) of neural networks is presented using the FPSOCM. Numerical example of neural network is given to illustrate that the performance of the FPSOCM is good for tuning the parameters (weights) of neural networks.

Citation
Ling, S. and Nguyen, H. and Chan, Kit. 2009. A new particle swarm optimization algorithm for neural network optimization, in Zhou, W. (ed), 2nd IEEE International Workshop on Data Mining and Artificial Intelligence (DMAI 2009) with Third International Conference on Network and System Security (NSS 2009), Oct 19 2009, pp. 516-521. Gold Coast, Australia: IEEE Computer Society.
Source Title
Proceedings of the 2nd IEEE international workshop on data mining and artificial intelligence (DMAI 2009) with third international conference on network and system security (NSS 2009)
URI
Faculty
Curtin Business School
The Digital Ecosystems and Business Intelligence Institute (DEBII)
Department
Digital Ecosystems and Business Intelligence Institute (DEBII)