Learn More
In this paper, a novel method based on feed-forward neural networks is presented for solving Fredholm integral equations of the second kind. In the present approach, we first approximate the unknown function based on neural networks, then substitute the approximate function in the appropriate error function of the integral equation, and finally train the(More)
In this paper, homotopy analysis method is directly extended to investigate nth order semi-differential equations and to derive their numerical solutions which is introduced by replacing some integer-order space derivatives by fractional derivatives. The fractional derivatives are described in the Caputo sense. So the homotopy analysis method for(More)
This paper deals with the solutions of fuzzy Fredholm integral equations using neural networks. Based on the parametric form of a fuzzy number, a Fredholm fuzzy integral equation converts to two systems of integral equations of the second kind in the crisp case. This method employs a growing neural network as the approximate solution of the integral(More)
  • 1