Variational learning for quantum artificial neural networks

TL;DR

This paper reviews recent quantum neural network implementations and introduces a variational approach for efficient quantum nodes, reducing circuit depth and enhancing pattern classification potential on near-term quantum hardware.

Contribution

It presents a novel variational method for quantum neural networks that decreases circuit complexity and improves performance in noisy environments.

Findings

Reduced quantum circuit depth for neuron activation

Effective performance with noisy measurement data

Compatibility with memory-efficient feed-forward architectures

Abstract

In the last few years, quantum computing and machine learning fostered rapid developments in their respective areas of application, introducing new perspectives on how information processing systems can be realized and programmed. The rapidly growing field of Quantum Machine Learning aims at bringing together these two ongoing revolutions. Here we first review a series of recent works describing the implementation of artificial neurons and feed-forward neural networks on quantum processors. We then present an original realization of efficient individual quantum nodes based on variational unsampling protocols. We investigate different learning strategies involving global and local layer-wise cost functions, and we assess their performances also in the presence of statistical measurement noise. While keeping full compatibility with the overall memory-efficient feed-forward architecture, our constructions effectively reduce the quantum circuit depth required to determine the activation probability of single neurons upon input of the relevant data-encoding quantum states. This suggests a viable approach towards the use of quantum neural networks for pattern classification on near-term quantum hardware.