A NEW STRATEGY FOR TRAINING RBF NETWORK WITH APPLICATIONS TO NONLINEAR INTEGRAL EQUATIONS

سال انتشار: 1387
نوع سند: مقاله ژورنالی
زبان: انگلیسی
مشاهده: 606

فایل این مقاله در 7 صفحه با فرمت PDF قابل دریافت می باشد

استخراج به نرم افزارهای پژوهشی:

لینک ثابت به این مقاله:

شناسه ملی سند علمی:

JR_IJIEPR-19-6_001

تاریخ نمایه سازی: 7 شهریور 1393

چکیده مقاله:

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.

نویسندگان

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