Detection of phase transition via convolutional neural network

TL;DR

This paper demonstrates that a CNN can identify phase transitions in the 2D Ising model without prior knowledge, introduces a new CNN-based order parameter, and highlights the importance of ReLU activation for this task.

Contribution

It presents a CNN approach that detects phase transitions and defines a new order parameter, advancing machine learning applications in statistical physics.

Findings

CNN successfully identifies phase transition features

New CNN-based order parameter approximates critical temperature

ReLU activation is crucial for detecting phase transitions

Abstract

We design a Convolutional Neural Network (CNN) which studies correlation between discretized inverse temperature and spin configuration of 2D Ising model and show that it can find a feature of the phase transition without teaching any a priori information for it. We also define a new order parameter via the CNN and show that it provides well approximated critical inverse temperature. In addition, we compare the activation functions for convolution layer and find that the Rectified Linear Unit (ReLU) is important to detect the phase transition of 2D Ising model.