Explaining the Machine Learning Solution of the Ising Model

Author:

Roberto C. Alamino

Keyword:

Condensed Matter, Disordered Systems and Neural Networks, Disordered Systems and Neural Networks (cond-mat.dis-nn), Machine Learning (cs.LG), Computational Physics (physics.comp-ph)

journal:

date:

2024-02-18 00:00:00

Abstract

As powerful as machine learning (ML) techniques are in solving problems involving data with large dimensionality, explaining the results from the fitted parameters remains a challenging task of utmost importance, especially in physics applications. Here it is shown how this can be accomplished for the ferromagnetic Ising model, the target of many ML studies in the last years. By using a neural network (NN) without any hidden layers and the symmetry of the Hamiltonian to find the critical temperature for the continuous phase transition of the model, an explanation of its strategy is found. This allows the prediction of the minimal extension of the NN to solve the problem when the symmetry is not known, which is also explainable.

PDF: Explaining the Machine Learning Solution of the Ising Model.pdf