A Neural Networks study of the phase transitions of Potts model

TL;DR

This study demonstrates that neural networks, trained on theoretical ground state configurations, effectively identify phase transitions in Potts models, matching traditional methods in efficiency and requiring minimal training data.

Contribution

The paper introduces a neural network approach trained on ground state configurations to analyze phase transitions in Potts models, showing its effectiveness and efficiency.

Findings

Neural networks can detect first-order phase transitions effectively.

Training on ground state configurations reduces data requirements.

The method performs comparably to Monte Carlo techniques.

Abstract

Using the techniques of Neural Networks (NN), we study the three-dimensional (3D) 5-state ferromagnetic Potts model on the cubic lattice as well as the two-dimensional (2D) 3-state antiferromagnetic Potts model on the square lattice. Unlike the conventional approach, here we follow the idea employed in Ann.~Phy.~391 (2018) 312-331. Specifically, instead of numerically generating numerous objects for the training, the whole or part of the theoretical ground state configurations of the studied models are considered as the training sets. Remarkably, our investigation of these two models provides convincing evidence for the effectiveness of the method of preparing training sets used in this study. In particular, the results of the 3D model obtained here imply that the NN approach is as efficient as the traditional method since the signal of a first order phase transition, namely tunneling between two channels, determined by the NN method is as strong as that calculated with the Monte Carlo technique. Furthermore, the outcomes associated with the considered 2D system indicate even little partial information of the ground states can lead to conclusive results regarding the studied phase transition. The achievements reached in our investigation demonstrate that the performance of NN, using certain amount of the theoretical ground state configurations as the training sets, is impressive.