A NEW STRATEGY FOR TRAINING RBF NETWORK WITH APPLICATIONS TO NONLINEAR INTEGRAL EQUATIONS
Publish place: International Journal of Industrial Engineering & Production Research، Vol: 19، Issue: 6
Publish Year: 1387
نوع سند: مقاله ژورنالی
زبان: English
View: 612
This Paper With 7 Page And PDF Format Ready To Download
- Certificate
- من نویسنده این مقاله هستم
استخراج به نرم افزارهای پژوهشی:
شناسه ملی سند علمی:
JR_IJIEPR-19-6_001
تاریخ نمایه سازی: 7 شهریور 1393
Abstract:
A new learning strategy is proposed for training of radial basis functions (RBF) network. We apply two different local optimization methods to update theoutput 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:
Authors
A. Golbabai
is with the Department of Mathematics, Iran University of Science and Technology, Tehran, Iran.
M. Mammadov
is with the School of Information & Mathematical Science, Ballarat University, Ballarat VIC, Australia.
S. Seifollahi
is with the Department of Mathematics, University of Mohaghegh Ardabili, Ardabil, Iran