Simplifying Hamiltonian and Lagrangian Neural Networks via Explicit Constraints

arXiv2010.13581MaRDI QIDQ6352255

Author name not available (Why is that?)

Publication date: 26 October 2020

Abstract: Reasoning about the physical world requires models that are endowed with the right inductive biases to learn the underlying dynamics. Recent works improve generalization for predicting trajectories by learning the Hamiltonian or Lagrangian of a system rather than the differential equations directly. While these methods encode the constraints of the systems using generalized coordinates, we show that embedding the system into Cartesian coordinates and enforcing the constraints explicitly with Lagrange multipliers dramatically simplifies the learning problem. We introduce a series of challenging chaotic and extended-body systems, including systems with N-pendulums, spring coupling, magnetic fields, rigid rotors, and gyroscopes, to push the limits of current approaches. Our experiments show that Cartesian coordinates with explicit constraints lead to a 100x improvement in accuracy and data efficiency.

Has companion code repository: https://github.com/mfinzi/constrained-hamiltonian-neural-networks

This page was built for publication: Simplifying Hamiltonian and Lagrangian Neural Networks via Explicit Constraints

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6352255)