QDCNN: Quantum Dilated Convolutional Neural Network

TL;DR

This paper introduces QDCNN, a hybrid quantum-classical neural network that extends dilated convolution to quantum settings, capturing larger context efficiently and outperforming existing quantum CNNs on image recognition tasks.

Contribution

The paper proposes a novel hybrid quantum-classical dilated convolutional neural network architecture that improves context capturing and computational efficiency.

Findings

QDCNN outperforms existing quantum CNNs in accuracy.

QDCNN reduces computational cost compared to traditional quantum convolutional networks.

Empirical results on MNIST and Fashion-MNIST demonstrate improved performance.

Abstract

In recent years, with rapid progress in the development of quantum technologies, quantum machine learning has attracted a lot of interest. In particular, a family of hybrid quantum-classical neural networks, consisting of classical and quantum elements, has been massively explored for the purpose of improving the performance of classical neural networks. In this paper, we propose a novel hybrid quantum-classical algorithm called quantum dilated convolutional neural networks (QDCNNs). Our method extends the concept of dilated convolution, which has been widely applied in modern deep learning algorithms, to the context of hybrid neural networks. The proposed QDCNNs are able to capture larger context during the quantum convolution process while reducing the computational cost. We perform empirical experiments on MNIST and Fashion-MNIST datasets for the task of image recognition and demonstrate that QDCNN models generally enjoy better performances in terms of both accuracy and computation efficiency compared to existing quantum convolutional neural networks (QCNNs).