Pattern capacity of a single quantum perceptron

TL;DR

This paper investigates the pattern capacity of a quantum perceptron model using statistical physics, aiming to understand its potential advantages over classical perceptrons in quantum machine learning.

Contribution

It provides a theoretical analysis of the pattern capacity of a continuous variable quantum perceptron, a key step in assessing quantum advantage in machine learning.

Findings

Quantifies the pattern capacity of the quantum perceptron model

Establishes a theoretical framework for analyzing quantum perceptrons

Provides insights into the potential of quantum models for learning tasks

Abstract

Recent developments in Quantum Machine Learning have seen the introduction of several models to generalize the classical perceptron to the quantum regime. The capabilities of these quantum models need to be determined precisely in order to establish if a quantum advantage is achievable. Here we use a statistical physics approach to compute the pattern capacity of a particular model of quantum perceptron realized by means of a continuous variable quantum system.