Symplectic ODE-Net: Learning Hamiltonian Dynamics with Control

arXiv:1909.12077v5 Announce Type: replace
Abstract: In this paper, we introduce Symplectic ODE-Net (SymODEN), a deep learning framework which can infer the dynamics of a physical system, given by an ordinary differential equation (ODE), from observed state trajectories. To achieve better generalization with fewer training samples, SymODEN incorporates appropriate inductive bias by designing the associated computation graph in a physics-informed manner. In particular, we enforce Hamiltonian dynamics with control to learn the underlying dynamics in a transparent way, which can then …

abstract arxiv bias control cs.lg cs.sy deep learning deep learning framework designing differential differential equation dynamics eess.sy equation framework inductive ordinary paper physics.comp-ph samples state stat.ml training type