Quantum Reservoir GAN

TL;DR

This paper introduces a Quantum Reservoir GAN that leverages quantum reservoir computers as generators, improving accuracy over existing quantum and classical methods in generating handwritten digits and images.

Contribution

It proposes a novel software-based Quantum Reservoir GAN that enhances generation accuracy compared to prior quantum and classical approaches.

Findings

Quantum Reservoir GAN outperforms Quantum GAN, Classical Neural Networks, and standard Quantum Reservoir Computers.

It successfully generates handwritten digits and images on CIFAR-10 and Fashion-MNIST datasets.

The approach demonstrates improved accuracy without hardware modifications.

Abstract

Quantum machine learning is known as one of the promising applications of quantum computers. Many types of quantum machine learning methods have been released, such as Quantum Annealer, Quantum Neural Network, Variational Quantum Algorithms, and Quantum Reservoir Computers. They can work, consuming far less energy for networks of equivalent size. Quantum Reservoir Computers, in particular, have no limit on the size of input data. However, their accuracy is not enough for practical use, and the effort to improve accuracy is mainly focused on hardware improvements. Therefore, we propose the approach from software called Quantum Reservoir Generative Adversarial Network (GAN), which uses Quantum Reservoir Computers as a generator of GAN. We performed the generation of handwritten single digits and monochrome pictures on the CIFAR-10 and Fashion-MNIST datasets. As a result, Quantum Reservoir GAN is confirmed to be more accurate than Quantum GAN, Classical Neural Network, and ordinary Quantum Reservoir Computers.