Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Qu, Guangkai, Wang, Zhimin, Zhong, Guoqiang, Gu, Yongjian
Format: Preprint
Veröffentlicht: 2025
Schlagworte:
Online-Zugang:https://arxiv.org/abs/2504.08487
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866917982602526720
author Qu, Guangkai
Wang, Zhimin
Zhong, Guoqiang
Gu, Yongjian
author_facet Qu, Guangkai
Wang, Zhimin
Zhong, Guoqiang
Gu, Yongjian
contents Quantum neural networks (QNNs) represent a pioneering intersection of quantum computing and deep learning. In this study, we unveil a fundamental convolution property inherent to QNNs, stemming from the natural parallelism of quantum gate operations on quantum states. Notably, QNNs are capable of performing a convolutional layer using a single quantum gate, whereas classical methods require 2^n basic operations. This essential property has been largely overlooked in the design of existing quantum convolutional neural networks (QCNNs), limiting their ability to capture key structural features of classical CNNs, including local connectivity, parameter sharing, and multi-channel, multi-layer architectures. To address these limitations, we propose novel QCNN architectures that explicitly harness the convolutional nature of QNNs. We validate the effectiveness of these architectures through extensive numerical experiments focused on multiclass image classification. Our findings provide deep insights into the realization of convolutional mechanisms within QNNs, marking a substantial advancement in the development of QCNNs and broadening their potential for efficient data processing.
format Preprint
id arxiv_https___arxiv_org_abs_2504_08487
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle The inherent convolution property of quantum neural networks
Qu, Guangkai
Wang, Zhimin
Zhong, Guoqiang
Gu, Yongjian
Quantum Physics
Quantum neural networks (QNNs) represent a pioneering intersection of quantum computing and deep learning. In this study, we unveil a fundamental convolution property inherent to QNNs, stemming from the natural parallelism of quantum gate operations on quantum states. Notably, QNNs are capable of performing a convolutional layer using a single quantum gate, whereas classical methods require 2^n basic operations. This essential property has been largely overlooked in the design of existing quantum convolutional neural networks (QCNNs), limiting their ability to capture key structural features of classical CNNs, including local connectivity, parameter sharing, and multi-channel, multi-layer architectures. To address these limitations, we propose novel QCNN architectures that explicitly harness the convolutional nature of QNNs. We validate the effectiveness of these architectures through extensive numerical experiments focused on multiclass image classification. Our findings provide deep insights into the realization of convolutional mechanisms within QNNs, marking a substantial advancement in the development of QCNNs and broadening their potential for efficient data processing.
title The inherent convolution property of quantum neural networks
topic Quantum Physics
url https://arxiv.org/abs/2504.08487