Generalization properties of restricted Boltzmann machine for short-range order

TL;DR

This paper explores the ability of restricted Boltzmann machines to model and predict short-range order in binary alloys, demonstrating their effectiveness in reproducing and generalizing thermodynamic properties across different concentrations.

Contribution

It introduces the use of RBMs for predicting alloy order parameters and thermodynamic properties beyond trained concentrations, showing their potential in materials modeling.

Findings

RBM accurately reproduces order parameters at trained concentrations.

RBM can predict properties at untrained alloy concentrations.

Demonstrates RBM's potential for materials property prediction.

Abstract

The restricted Boltzmann machine (RBM) is used to investigate short-range order in binary alloys. The network is trained on the data collected by Monte Carlo simulations for a simple Ising-like binary alloy model and used to calculate the Warren--Cowley short-range order parameter and other thermodynamic properties. We demonstrate that RBM not only reproduces the order parameters for the alloy concentration at which it was trained, but can also predict them for any other concentrations.