A Novel Elliptical Basis Function Neural Networks Optimized by Particle Swarm Optimization

In this paper, a novel model of elliptical basis function neural networks (EBFNN) is proposed. Firstly, a geometry analytic algorithm is applied to construct the hyper-ellipsoid units of hidden layer of the EBFNN, i.e., an initial structure of the EBFNN, which is further pruned by the particle swarm...

Full description

Saved in:
Bibliographic Details
Published inAdvances in Neural Networks - ISNN 2006 pp. 747 - 751
Main Authors Du, Ji-Xiang, Zhai, Chuan-Min, Wang, Zeng-Fu, Zhang, Guo-Jun
Format Book Chapter Conference Proceeding
LanguageEnglish
Published Berlin, Heidelberg Springer Berlin Heidelberg 2006
Springer
SeriesLecture Notes in Computer Science
Subjects
Applied sciences
Artificial intelligence
Computer science; control theory; systems
Connectionism. Neural networks
Exact sciences and technology
Good Generalization Performance
Hybrid Particle Swarm Optimization
Particle Swarm Optimization
Radial Basis Function Neural Network
Radial Basis Function Neural Network Model
Swarm intelligence
Neural network
Ellipsoid
Modeling
Optimization
Analytic geometry
Online AccessGet full text

Cover

More Information
Summary:In this paper, a novel model of elliptical basis function neural networks (EBFNN) is proposed. Firstly, a geometry analytic algorithm is applied to construct the hyper-ellipsoid units of hidden layer of the EBFNN, i.e., an initial structure of the EBFNN, which is further pruned by the particle swarm optimization (PSO) algorithm. Finally, the experimental results demonstrated the proposed hybrid optimization algorithm for the EBFNN model is feasible and efficient, and the EBFNN is not only parsimonious but also has better generalization performance than the RBFNN.
ISBN:354034439X
9783540344391
ISSN:0302-9743
1611-3349
DOI:10.1007/11759966_109