Regression-based neural network training for the solution of ordinary differential equations (Q391689)

Summary: We introduce a method which is based on the use of an unsupervised type of regression-based algorithm (RBA) for solving ordinary differential equations (ODEs) with initial or boundary conditions. The approximate solution of the differential equation is differentiable and closed analytic. Here we use an error back propagation method for minimising the error function and a modification of the parameters without direct use of other optimisation techniques. Initial weights are taken as combination of random as well as by the proposed regression-based method. We present the method for solving a variety of problems and the results with arbitrary and regression-based initial weights are compared. Here the number of nodes in the hidden layer has been fixed according to the degree of the polynomial in the regression. The present model demonstrates how to get also the approximate solutions for the differential equation inside and outside of the training domain.