Three-phase strategy for the OSD learning method in RBF neural networks

Authors:
Gh. A. Montazer;Reza Sabzevari;Fatemeh Ghorbani
Affiliations:
School of Engineering, Tarbiat Modares University, P.O. Box 14115-179, Tehran, Iran;School of Engineering, Islamic Azad University of Qazvin, Member of YRC, P.O. Box 14115-179, Tehran, Iran;School of Basic Sciences, Tarbiat Modares University, P.O. Box 14115-179, Tehran, Iran
Venue:
Neurocomputing
Year:
2009

Citing 11
Cited 6

Neural Networks

Neural Networks
Neural Networks for Pattern Recognition

Neural Networks for Pattern Recognition
Neural Networks: A Comprehensive Foundation

Neural Networks: A Comprehensive Foundation
Three learning phases for radial-basis-function networks

Neural Networks
Alternatives to the k-means algorithm that find better clusterings

Proceedings of the eleventh international conference on Information and knowledge management
A comparative analysis of neural network performances in astronomical imaging

Applied Numerical Mathematics
Learning methods for radial basis function networks

Future Generation Computer Systems
Improvement of learning algorithms for RBF neural networks in a helicopter sound identification system

Neurocomputing
Least-mean-square training of cluster-weighted modeling

ICANN'07 Proceedings of the 17th international conference on Artificial neural networks
Growing radial basis neural networks: merging supervised and unsupervised learning with network growth techniques

IEEE Transactions on Neural Networks
Decision trees can initialize radial-basis function networks

IEEE Transactions on Neural Networks

Radial Basis Function network learning using localized generalization error bound

Information Sciences: an International Journal
A fast multi-output RBF neural network construction method

Neurocomputing
Original papers: A calibration method of detecting soil water content based on the information-sharing in wireless sensor network

Computers and Electronics in Agriculture
A novel locally regularized automatic construction method for RBF neural models

Neurocomputing
An improvement in RBF learning algorithm based on PSO for real time applications

Neurocomputing
Improvement of RBF neural networks using Fuzzy-OSD algorithm in an online radar pulse classification system

Applied Soft Computing

Quantified Score

Hi-index	0.01

Visualization

Abstract

This paper presents a novel approach in learning algorithms commonly used for training radial basis function (RBF) neural networks. This approach could be used in applications that need real-time capabilities for retraining RBF neural networks. The proposed method is a Three-Phase Learning Algorithm that optimizes the functionality of the Optimum Steepest Decent (OSD) learning method. This methodology focuses to attain greater precision in initializing the center and width of RBF units. An RBF neural network with well-adjusted RBF units in the train process will result in better performance in network response. This method is proposed to reach better performance for RBF neural networks in fewer train iterations, which is the critical issue in real-time applications. Comparing results employing different learning strategies shows interesting outcomes as have come out in this paper.