Solving Fractional Order Differential Equations Using Artificial Neural Network

Abstract

In this thesis, we find the solution of fractional order differential equations using Arti ficial Neural Network(ANN). In this study artificial neural network technique is devel oped to find solution of fractional order differential equations(FODE). The fractional differential equation has the advantage of being able to better represent a variety of real-world physical system application challenges. Here we have employed multi-layer feed forward neural architecture and error back propagation algorithm with unsupervised learning for minimizing the error function and modification of the parameters (weights and biases). Finally we compared the analytical solution and ANN solution for some illustrative examples.