Learning Physics from Data: a Thermodynamic Interpretation
Abstract
Experimental data bases are typically very large and high dimensional. To learn from them requires to recognize important features (a pattern), often present at scales different to that of the recorded data. Following the experience collected in statistical mechanics and thermodynamics, the process of recognizing the pattern (the learning process) can be seen as a dissipative time evolution driven by entropy from a detailed level of description to less detailed. This is the way thermodynamics enters machine learning. On the other hand, reversible (typically Hamiltonian) evolution is propagation within the levels of description, that is also to be recognized. This is how Poisson geometry enters machine learning. Learning to handle free surface liquids and damped rigid body rotation serves as an illustration.
Cite
@article{arxiv.1909.01074,
title = {Learning Physics from Data: a Thermodynamic Interpretation},
author = {Francisco Chinesta and Elias Cueto and Miroslav Grmela and Beatriz Moya and Michal Pavelka and Martin Sipka},
journal= {arXiv preprint arXiv:1909.01074},
year = {2021}
}
Comments
Submitted to the proceedings of the Les Houches Summer School