Quantum-inspired Complex Convolutional Neural Networks

TL;DR

This paper introduces quantum-inspired complex-valued convolutional neural networks that leverage richer representations and demonstrate improved classification accuracy on datasets like MNIST compared to classical CNNs.

Contribution

It extends quantum-inspired neurons to convolutional layers using complex weights, creating novel QICNN models with enhanced performance.

Findings

QICNNs outperform classical CNNs on MNIST in accuracy.

Five different QICNN structures are proposed and analyzed.

QICNNs show potential for better performance in various learning tasks.

Abstract

Quantum-inspired neural network is one of the interesting researches at the junction of the two fields of quantum computing and deep learning. Several models of quantum-inspired neurons with real parameters have been proposed, which are mainly used for three-layer feedforward neural networks. In this work, we improve the quantum-inspired neurons by exploiting the complex-valued weights which have richer representational capacity and better non-linearity. We then extend the method of implementing the quantum-inspired neurons to the convolutional operations, and naturally draw the models of quantum-inspired convolutional neural networks (QICNNs) capable of processing high-dimensional data. Five specific structures of QICNNs are discussed which are different in the way of implementing the convolutional and fully connected layers. The performance of classification accuracy of the five QICNNs are tested on the MNIST and CIFAR-10 datasets. The results show that the QICNNs can perform better in classification accuracy on MNIST dataset than the classical CNN. More learning tasks that our QICNN can outperform the classical counterparts will be found.