|
|
|
|
A New Strategy for Training RBF Network with Applications to Nonlinear Integral Equations
|
|
|
|
|
|
|
|
نویسنده
|
Golbabai A. ,Mammadov M. ,Seifollahi S.
|
|
منبع
|
international journal of industrial engineering and production research - 2008 - دوره : 19 - شماره : 5-2 - صفحه:1 -8
|
|
چکیده
|
A new learning strategy is proposedfor training ofradial basis functions (ref) 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.
|
|
کلیدواژه
|
REF network ,Gradient method ,Newton's method ,Nonlinear integral equations
|
|
آدرس
|
iran university of science and technology, Department of Mathematics, ایران, Ballarat University, School of Information & Mathematical Science, Australia, university of mohaghegh ardabili, Department of Mathematics, ایران
|
|
پست الکترونیکی
|
sattarseif@gmail.com
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
Authors
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|