Identifying Quantum Phase Transitions using Artificial Neural Networks on Experimental Data

TL;DR

This paper demonstrates how artificial neural networks can analyze experimental quantum data to identify phase transitions and map complex phase diagrams, surpassing traditional methods.

Contribution

It introduces a neural network approach for analyzing experimental quantum gas data to detect phase transitions and characterize phase diagrams without prior knowledge of Hamiltonians.

Findings

Successfully mapped the Haldane model's topological phase diagram

Accurately characterized the superfluid-to-Mott-insulator transition

Demonstrated neural networks' ability to analyze complex experimental quantum data

Abstract

Machine learning techniques such as artificial neural networks are currently revolutionizing many technological areas and have also proven successful in quantum physics applications. Here we employ an artificial neural network and deep learning techniques to identify quantum phase transitions from single-shot experimental momentum-space density images of ultracold quantum gases and obtain results, which were not feasible with conventional methods. We map out the complete two-dimensional topological phase diagram of the Haldane model and provide an accurate characterization of the superfluid-to-Mott-insulator transition in an inhomogeneous Bose-Hubbard system. Our work points the way to unravel complex phase diagrams of general experimental systems, where the Hamiltonian and the order parameters might not be known.