Design Fast Feed Forward Neural Network to Solve Initial Value Problems

Abstract

The aim of this paper is to design fast feed forward neural network to present a method to solve initial value problems for ordinary differential equations. That is to develop an algorithm which can speedup the solution times, reduce solver failures, and increase possibility of obtaining the globally optimal solution.And we use several different training algorithms many of them having a very fast convergence rate for reasonable size networks.Finally, we illustrate the method by solving model problem and present comparison with solutions obtained using other different methods