Quantum State Reconstruction in a Noisy Environment via Deep Learning

TL;DR

This paper demonstrates that deep learning can effectively reconstruct and classify quantum states affected by noise, achieving high fidelities and perfect classification accuracy in noisy quantum environments.

Contribution

It introduces a neural network approach for quantum state reconstruction and noise classification, surpassing traditional methods in noisy quantum systems.

Findings

Reconstruction fidelities exceeding 99% for up to three qubits.

Neural network classifier achieves perfect accuracy in distinguishing noisy channels.

Effective handling of various single- and two-qubit noisy channels.

Abstract

Quantum noise is currently limiting efficient quantum information processing and computation. In this work, we consider the tasks of reconstructing and classifying quantum states corrupted by the action of an unknown noisy channel using classical feedforward neural networks. By framing reconstruction as a regression problem, we show how such an approach can be used to recover with fidelities exceeding 99% the noiseless density matrices of quantum states of up to three qubits undergoing noisy evolution, and we test its performance with both single-qubit (bit-flip, phase-flip, depolarising, and amplitude damping) and two-qubit quantum channels (correlated amplitude damping). Moreover, we also consider the task of distinguishing between different quantum noisy channels, and show how a neural network-based classifier is able to solve such a classification problem with perfect accuracy.