Volume 19, Issue 6 (IJES 2008)                   IJIEPR 2008, 19(6): 1-7 | Back to browse issues page

XML Print

Download citation:
BibTeX | RIS | EndNote | Medlars | ProCite | Reference Manager | RefWorks
Send citation to:
Golbabai A, Mammadov M, Seifollahi S. A New Strategy for Training RBF Network with Applications to Nonlinear Integral Equations . IJIEPR 2008; 19 (6) :1-7
URL: http://ijiepr.iust.ac.ir/article-1-142-en.html
A New Strategy for Training RBF Network with Applications to Nonlinear Integral Equations
A. Golbabai 1, M. Mammadov , S. Seifollahi
1- , m.mammadov@ballarat.edu.au
Abstract:   (8318 Views)

A new learning strategy is proposed for training of radial basis functions (RBF) network. We apply two different local optimization methods to update the output weights in training process, the gradient method and a combination of the gradient and Newton methods. Numerical results obtained in solving nonlinear integral equations show the excellent performance of the combined gradient method in comparison with gradient method as local back propagation algorithms.

Keywords: RBF network, Gradient method, Newton\'s method, Nonlinear integral equations
Full-Text [PDF 121 kb]   (2217 Downloads)    
Type of Study: Research | Subject: Other Related Subject
Received: 2010/07/20 | Published: 2008/08/15
Add your comments about this article : Your username or Email:
CAPTCHA
Send email to the article author

Rights and permissions
Creative Commons License This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.