13: Unsupervised ANN model for solving fractional differential equations

Arup Kumar Sahoo; S. Chakraverty    Department of Mathematics, National Institute of Technology Rourkela, Rourkela, Odisha, India

Abstract

In this chapter, a neural network model for solving fractional differential equations is described. This model is based on approximating the solution by using power series expansion and a modified loss function. The fractional derivatives are considered in the Caputo sense in the present work. The results obtained by the neural network approach are compared with existing solutions in various tables and figures to illustrate the efficacy of the presented method. Furthermore, different error analyses have been conducted to validate the accuracy ...

Get Computation and Modeling for Fractional Order Systems now with the O’Reilly learning platform.

O’Reilly members experience books, live events, courses curated by job role, and more from O’Reilly and nearly 200 top publishers.