Solving physics-based initial value problems with unsupervised machine learning.

Abstract

Initial value problems-a system of ordinary differential equations and corresponding initial conditions-can be used to describe many physical phenomena including those arise in classical mechanics. We have developed an approach to solve physics-based initial value problems using unsupervised machine learning. We propose a deep learning framework that models the dynamics of a variety of mechanical systems through neural networks. Our framework is flexible, allowing us to solve nonlinear, coupled, and chaotic dynamical systems. We demonstrate the effectiveness of our approach on systems including a free particle, a particle in a gravitational field, a classical pendulum, and the Hénon-Heiles system (a pair of coupled harmonic oscillators with a nonlinear perturbation, used in celestial mechanics). Our results show that deep neural networks can successfully approximate solutions to these problems, producing trajectories which conserve physical properties such as energy and those with stationary action. We note that probabilistic activation functions, as defined in this paper, are required to learn any solutions of initial value problems in their strictest sense, and we introduce coupled neural networks to learn solutions of coupled systems.