English

Benchmarking Energy-Conserving Neural Networks for Learning Dynamics from Data

Machine Learning 2023-05-02 v6 Artificial Intelligence Systems and Control Systems and Control Dynamical Systems

Abstract

The last few years have witnessed an increased interest in incorporating physics-informed inductive bias in deep learning frameworks. In particular, a growing volume of literature has been exploring ways to enforce energy conservation while using neural networks for learning dynamics from observed time-series data. In this work, we survey ten recently proposed energy-conserving neural network models, including HNN, LNN, DeLaN, SymODEN, CHNN, CLNN and their variants. We provide a compact derivation of the theory behind these models and explain their similarities and differences. Their performance are compared in 4 physical systems. We point out the possibility of leveraging some of these energy-conserving models to design energy-based controllers.

Keywords

Cite

@article{arxiv.2012.02334,
  title  = {Benchmarking Energy-Conserving Neural Networks for Learning Dynamics from Data},
  author = {Yaofeng Desmond Zhong and Biswadip Dey and Amit Chakraborty},
  journal= {arXiv preprint arXiv:2012.02334},
  year   = {2023}
}
R2 v1 2026-06-23T20:43:21.471Z