NeurIPS 2019poster1238 citations
Hamiltonian Neural Networks
Samuel Greydanus, Misko Dzamba, Jason Yosinski
Abstract
Even though neural networks enjoy widespread use, they still struggle to learn the basic laws of physics. How might we endow them with better inductive biases? In this paper, we draw inspiration from Hamiltonian mechanics to train models that learn and respect exact conservation laws in an unsupervised manner. We evaluate our models on problems where conservation of energy is important, including the two-body problem and pixel observations of a pendulum. Our model trains faster and generalizes better than a regular neural network. An interesting side effect is that our model is perfectly reversible in time.
BibTeX
@inproceedings{NEURIPS2019_26cd8eca,
author = {Greydanus, Samuel and Dzamba, Misko and Yosinski, Jason},
booktitle = {Advances in Neural Information Processing Systems},
editor = {H. Wallach and H. Larochelle and A. Beygelzimer and F. d\textquotesingle Alch\'{e}-Buc and E. Fox and R. Garnett},
pages = {},
publisher = {Curran Associates, Inc.},
title = {Hamiltonian Neural Networks},
url = {https://proceedings.neurips.cc/paper_files/paper/2019/file/26cd8ecadce0d4efd6cc8a8725cbd1f8-Paper.pdf},
volume = {32},
year = {2019}
}