Improved Tomographic Estimates by Specialised Neural Networks

TL;DR

This paper introduces a specialized neural network with a convolutional stage that enhances quantum process tomography, achieving reliable parameter estimation from classical data using only simulated training, thus offering a new paradigm for quantum system characterization.

Contribution

The paper presents a novel neural network architecture with a convolutional stage that improves quantum process tomography using simulated data for training.

Findings

Neural network with convolutional stage improves parameter estimates.

Reliable operation achieved with training solely on simulated data.

Demonstrates effectiveness for quantum channel characterization.

Abstract

Characterization of quantum objects, being them states, processes, or measurements, complemented by previous knowledge about them is a valuable approach, especially as it leads to routine procedures for real-life components. To this end, Machine Learning algorithms have demonstrated to successfully operate in presence of noise, especially for estimating specific physical parameters. Here we show that a neural network (NN) can improve the tomographic estimate of parameters by including a convolutional stage. We applied our technique to quantum process tomography for the characterization of several quantum channels. We demonstrate that a stable and reliable operation is achievable by training the network only with simulated data. The obtained results show the viability of this approach as an effective tool based on a completely new paradigm for the employment of NNs operating on classical data produced by quantum systems.