Quantum entanglement recognition

TL;DR

This paper introduces a machine learning framework using convolutional neural networks to accurately recognize quantum entanglement from statistical images of quantum many-body states, applicable in various quantum systems.

Contribution

It presents a novel protocol for generating and classifying statistical images to detect entanglement, offering a generally applicable and accurate recognition method.

Findings

High accuracy in entanglement detection across diverse quantum states

Controlled error rates in the recognition process

Potential for experimental quantification of quantum entanglement

Abstract

Entanglement constitutes a key characteristic feature of quantum matter. Its detection, however, still faces major challenges. In this letter, we formulate a framework for probing entanglement based on machine learning techniques. The central element is a protocol for the generation of statistical images from quantum many-body states, with which we perform image classification by means of convolutional neural networks. We show that the resulting quantum entanglement recognition task is accurate and can be assigned a well-controlled error across a wide range of quantum states. We discuss the potential use of our scheme to quantify quantum entanglement in experiments. Our developed scheme provides a generally applicable strategy for quantum entanglement recognition in both equilibrium and nonequilibrium quantum matter.