Scalable quantum neural networks by few quantum resources

TL;DR

This paper proposes a scalable quantum neural network model that uses minimal quantum resources by executing swap tests over few qubits, offering a promising approach for efficient quantum machine learning.

Contribution

It introduces a general parametric quantum neural network model based on swap tests and small modules, enhancing scalability with limited quantum resources.

Findings

Model is equivalent to a two-layer feedforward neural network

Uses few qubits through swap tests and measurement protocols

Discusses advantages and future perspectives of the quantum approach

Abstract

This paper focuses on the construction of a general parametric model that can be implemented executing multiple swap tests over few qubits and applying a suitable measurement protocol. The model turns out to be equivalent to a two-layer feedforward neural network which can be realized combining small quantum modules. The advantages and the perspectives of the proposed quantum method are discussed.