Analyzing non-equilibrium quantum states through snapshots with artificial neural networks

TL;DR

This paper demonstrates how neural networks can analyze experimental quantum snapshots to distinguish non-equilibrium states from thermalized states, aiding the study of complex quantum dynamics and phase transitions.

Contribution

It introduces a machine learning approach to identify thermalization in non-equilibrium quantum states using experimental data, enabling analysis of larger, entangled systems.

Findings

Neural networks successfully distinguish non-equilibrium from thermal states.

Method applied to experimental ultracold atom data.

Provides a scalable tool for analyzing large quantum systems.

Abstract

Current quantum simulation experiments are starting to explore non-equilibrium many-body dynamics in previously inaccessible regimes in terms of system sizes and time scales. Therefore, the question emerges which observables are best suited to study the dynamics in such quantum many-body systems. Using machine learning techniques, we investigate the dynamics and in particular the thermalization behavior of an interacting quantum system which undergoes a dynamical phase transition from an ergodic to a many-body localized phase. A neural network is trained to distinguish non-equilibrium from thermal equilibrium data, and the network performance serves as a probe for the thermalization behavior of the system. We test our methods with experimental snapshots of ultracold atoms taken with a quantum gas microscope. Our results provide a path to analyze highly-entangled large-scale quantum states for system sizes where numerical calculations of conventional observables become challenging.