Dissipative SymODEN: Encoding Hamiltonian Dynamics with Dissipation and Control into Deep Learning

Yaofeng Desmond Zhong, Biswadip Dey, Amit Chakraborty

Keywords: Deep Learning, Physics-induced Prior, Transparency

TL;DR: We propose a deep learning architecture which encodes a non-conservative physics, namely Hamiltonian dynamics with external input and energy dissipation, to improve generalization, transparency, and data efficiency.

Abstract: In this work, we introduce Dissipative SymODEN a deep learning architecture which can infer the dynamics of a physical system with dissipation from observed state trajectories. To improve prediction accuracy while reducing network size, Dissipative SymODEN encodes the port-Hamiltonian dynamics with energy dissipation and external input into the design of its computation graph and learns the dynamics in a structured way. The learned model, by revealing key aspects of the system, such as the inertia, dissipation, and potential energy, paves the way for energy-based controllers.