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

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.

Cite

Text

Zhong et al. "Dissipative SymODEN: Encoding Hamiltonian Dynamics with Dissipation and Control into Deep Learning." ICLR 2020 Workshops: DeepDiffEq, 2020.

Markdown

[Zhong et al. "Dissipative SymODEN: Encoding Hamiltonian Dynamics with Dissipation and Control into Deep Learning." ICLR 2020 Workshops: DeepDiffEq, 2020.](https://mlanthology.org/iclrw/2020/zhong2020iclrw-dissipative/)

BibTeX

@inproceedings{zhong2020iclrw-dissipative,
  title     = {{Dissipative SymODEN: Encoding Hamiltonian Dynamics with Dissipation and Control into Deep Learning}},
  author    = {Zhong, Yaofeng Desmond and Dey, Biswadip and Chakraborty, Amit},
  booktitle = {ICLR 2020 Workshops: DeepDiffEq},
  year      = {2020},
  url       = {https://mlanthology.org/iclrw/2020/zhong2020iclrw-dissipative/}
}