Neural-network-based parameter estimation for quantum detection

TL;DR

This paper demonstrates that neural networks can effectively estimate parameters in quantum detection tasks, especially when physical models are complex or data is limited, exemplified with atomic sensors.

Contribution

It introduces a neural-network-based protocol for quantum parameter estimation that requires minimal prior knowledge and handles complex sensor responses.

Findings

Neural networks accurately estimate quantum sensor parameters.

Method works under high shot noise and limited measurements.

Applicable to various quantum detection scenarios.

Abstract

Artificial neural networks bridge input data into output results by approximately encoding the function that relates them. This is achieved after training the network with a collection of known inputs and results leading to an adjustment of the neuron connections and biases. In the context of quantum detection schemes, neural networks find a natural playground. In particular, in the presence of a target, a quantum sensor delivers a response, i.e., the input data, which can be subsequently processed by a neural network that outputs the target features. We demonstrate that adequately trained neural networks enable to characterize a target with minimal knowledge of the underlying physical model, in regimes where the quantum sensor presents complex responses, and under a significant shot noise due to a reduced number of measurements. We exemplify the method with a development for $^{171}$Yb$^{+}$ atomic sensors. However, our protocol is general, thus applicable to arbitrary quantum detection scenarios.