Detected the steerability bounds of the generalized Werner states via BackPropagation neural network

TL;DR

This paper employs backpropagation neural networks to classify quantum steerability and accurately predict steerability bounds of generalized Werner states, outperforming traditional methods with less measurement data.

Contribution

It introduces a neural network-based approach for quantum steerability classification and bounds prediction, achieving higher accuracy with partial measurement data.

Findings

Neural networks outperform SVM in quantum steerability classification.

Predicted steerability bounds closely match theoretical bounds.

High-performance classifiers require only three fixed measurement directions.

Abstract

We use error BackPropagation (BP) neural network to determine whether an arbitrary two-qubit quantum state is steerable and optimize the steerability bounds of the generalized Werner state. The results show that no matter how we choose the features for the quantum states, we can use the BP neural network to construct several models to realize high-performance quantum steering classifiers compared with the support vector machine (SVM). In addition, we predict the steerability bounds of the generalized Werner states by using the classifiers which are newly constructed by the BP neural network, that is, the predicted steerability bounds are closer to the theoretical bounds. In particular, high-performance classifiers with partial information of the quantum states which we only need to measure in three fixed measurement directions are obtained.