# A thermal quantum classifier

## TL;DR

This paper demonstrates that a two-level quantum system in thermal environments can serve as an efficient thermal quantum classifier, enabling faster and potentially more effective thermal neural networks compared to classical models.

## Contribution

It introduces a novel thermal quantum classifier based on open quantum systems interacting with thermal reservoirs, advancing quantum neural network design.

## Key findings

- Quantum systems can classify temperature information effectively.
- Thermal quantum classifiers operate faster than classical counterparts.
- Proposed models are feasible with realistic parameters.

## Abstract

A data classifier is the basic structural unit of an artificial neural network. These classifiers, known as perceptron, make an output prediction over the linear summation of the input information. Quantum versions of artificial neural networks are considered to provide more efficient and faster artificial intelligence and learning algorithms. The most generic and realistic open quantum systems are the quantum systems in thermal environments and the information carried by the thermal reservoirs is the temperature information. This study shows that an open quantum system that is in contact with many information channels is a natural information classifier. More specifically, it has been demonstrated that a two-level quantum system can classify temperature information of distinct thermal reservoirs. The results of the manuscript are of importance to the construction of thermal quantum neural networks and the development of minimal quantum thermal machines. Also, a physical model, proposed and discussed with realistic parameters, shows that faster operating thermal quantum classifiers can be built than the classical versions.