A quantum collisional classifier driven by information reservoir

TL;DR

This paper introduces a quantum collisional classifier that uses a dissipative model to classify quantum information in reservoir qubits, enabling applications in quantum machine learning and parameter estimation.

Contribution

It presents a novel dissipative classification scheme based on a collision model, linking quantum information processing with steady-state dynamics.

Findings

Binary classification of reservoir qubits achieved in steady state

Classification rule derived from micromaser-like master equation

Scheme applicable to quantum parameter estimation and supervised learning

Abstract

We investigate the open dynamics of a probe qubit weakly interacting with distinct qubit environments bearing quantum information. We show that the proposed dissipative model yields a binary classification of the reservoir qubits' quantum information in the steady state in the Bloch qubit parameter space, depending on the coupling rates. To describe the dissipation model dynamics, we have adopted the collision model, in which the input information parameters of the reservoir qubits are easily determined. We develop a generalized classification rule based on the results of the micromaser-like master equation where the classification can be described in terms of the Bloch parameters. Moreover, we show that the proposed classification scheme can also be achieved through quantum parameter estimation. Finally, we demonstrate that the proposed dissipative classification scheme is suitable for gradient descent based supervised learning tasks.