Deep learning, Differential equations, Artificial intelligence
Abstract
This article describes a method for the numerical solution of ordinary differential equations using an artificial neural network. Unlike other reported methods, the loss function is constructed from the same formalization of the differential equation and is done using Pytorch's computational resources for automatic differentiation. The proposed method is applied to the solution of four types of differential equations and the results obtained are shown. The design of the resulting neural network was aimed at its subsequent implementation in reconfigurable logic.
