We introduce a machine-learning approach (denoted Symmetry Seeker Neural Network) capable of automatically discovering discrete symmetry groups in physical systems. This method identifies the finite set of parameter transformations that preserve the system's physical properties. Remarkably, the method accomplishes this without prior knowledge of the system's symmetry or the mathematical relationships between parameters and properties. Demonstrating its versatility, we showcase examples from mathematics, nanophotonics, and quantum chemistry.
@article{arxiv.2307.13457,
title = {Finding discrete symmetry groups via Machine Learning},
author = {Pablo Calvo-Barlés and Sergio G. Rodrigo and Eduardo Sánchez-Burillo and Luis Martín-Moreno},
journal= {arXiv preprint arXiv:2307.13457},
year = {2023}
}