# Calibration of quantum sensors by neural networks

## TL;DR

This paper demonstrates that neural networks can effectively calibrate quantum photonic sensors using limited training data, reducing resource overheads and achieving high accuracy, potentially establishing a new standard calibration method.

## Contribution

It introduces a neural network-based calibration method for quantum sensors that requires minimal resources and relies solely on available probe states.

## Key findings

- Neural networks can calibrate quantum sensors with limited data.
- Covering the parameter space finely improves calibration accuracy.
- The method approaches the ultimate uncertainty limits.

## Abstract

Introducing quantum sensors as solution to real-world problem demands reliability and controllability outside laboratory conditions. Producers and operators ought to be assumed to have limited resources ready available for calibration, and yet, they should be able to trust the devices. Neural networks are almost ubiquitous for similar tasks for classical sensors: here we show the applications of this technique to calibrating a quantum photonic sensor. This is based on a set of training data, collected only relying on the available probe states, hence reducing overheads. We found that covering finely the parameter space is key to achieve uncertainties close to their ultimate level. This technique has potential to become the standard approach to calibrate quantum sensors.