Machine Learning the Square-Lattice Ising Model
Disordered Systems and Neural Networks
2022-04-01 v2
Abstract
Recently, machine-learning methods have been shown to be successful in identifying and classifying different phases of the square-lattice Ising model. We study the performance and limits of classification and regression models. In particular, we investigate how accurately the correlation length, energy and magnetisation can be recovered from a given configuration. We find that a supervised learning study of a regression model yields good predictions for magnetisation and energy, and acceptable predictions for the correlation length.
Cite
@article{arxiv.2111.13413,
title = {Machine Learning the Square-Lattice Ising Model},
author = {Burak Çivitcioğlu and Rudolf A. Römer and Andreas Honecker},
journal= {arXiv preprint arXiv:2111.13413},
year = {2022}
}
Comments
6 pages, 5 figures, submitted to the Proceedings for XXXII IUPAP Conference on Computational Physics (2021)