International Journal of Industrial Engineering & Production Research

 Abstract: In this paper homotopy perturbation is applied to system of linear Fredholm integral equations of the first kind .For these systems, degenerate kernels are considered and in order to avoid successive integrations ,an easy matrix computation is derived for approximating the solution of the problem.

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.