基于参数化量子电路的量子卷积神经网络模型及应用

Jin Zheng; Qing Gao; Yan Xuan Lü; Dao Yi Dong; Yu Pan

doi:10.7641/CTA.2021.10786

基于参数化量子电路的量子卷积神经网络模型及应用

Translated title of the contribution: Quantum convolutional neural network and applications for parameterized quantum circuits

Jin Zheng
, Qing Gao^*
, Yan Xuan Lü
, Dao Yi Dong
, Yu Pan

^*Corresponding author for this work

School of Automation Science and Electrical Engineering

Beihang University
University of Duisburg-Essen
University of New South Wales
Zhejiang University

Research output: Contribution to journal › Article › peer-review

5 Scopus citations

Abstract

Quantum neural networks have provided entirely new insight into the future of artificial intelligence by combining the advantages of quantum computing technologies and classical neural network models. In this paper, a parameterized quantum circuit based quantum convolutional neural network model is proposed, which can deal with both Euclidean data and non-Euclidean data and accelerate classical machine learning tasks by taking the computational advantages of quantum systems. Simulation results on the MNIST data set show that the model has strong learning ability and good generalization performance.

Translated title of the contribution	Quantum convolutional neural network and applications for parameterized quantum circuits
Original language	Chinese (Traditional)
Pages (from-to)	1772-1784
Number of pages	13
Journal	Kongzhi Lilun Yu Yingyong/Control Theory and Applications
Volume	38
Issue number	11
DOIs	https://doi.org/10.7641/CTA.2021.10786
State	Published - Nov 2021

Access to Document

10.7641/CTA.2021.10786

Cite this

@article{accec89c253a41559019fa25195b746c,

title = "基于参数化量子电路的量子卷积神经网络模型及应用",

abstract = "Quantum neural networks have provided entirely new insight into the future of artificial intelligence by combining the advantages of quantum computing technologies and classical neural network models. In this paper, a parameterized quantum circuit based quantum convolutional neural network model is proposed, which can deal with both Euclidean data and non-Euclidean data and accelerate classical machine learning tasks by taking the computational advantages of quantum systems. Simulation results on the MNIST data set show that the model has strong learning ability and good generalization performance.",

keywords = "Quantum convolutional neural network, Quantum graph convolutional neural network, Quantum machine learning, Quantum neural network",

author = "Jin Zheng and Qing Gao and L{\"u}, \{Yan Xuan\} and Dong, \{Dao Yi\} and Yu Pan",

year = "2021",

month = nov,

doi = "10.7641/CTA.2021.10786",

language = "繁体中文",

volume = "38",

pages = "1772--1784",

journal = "Kongzhi Lilun Yu Yingyong/Control Theory and Applications",

issn = "1000-8152",

publisher = "South China University of Technology",

number = "11",

}

TY - JOUR

T1 - 基于参数化量子电路的量子卷积神经网络模型及应用

AU - Zheng, Jin

AU - Gao, Qing

AU - Lü, Yan Xuan

AU - Dong, Dao Yi

AU - Pan, Yu

PY - 2021/11

Y1 - 2021/11

N2 - Quantum neural networks have provided entirely new insight into the future of artificial intelligence by combining the advantages of quantum computing technologies and classical neural network models. In this paper, a parameterized quantum circuit based quantum convolutional neural network model is proposed, which can deal with both Euclidean data and non-Euclidean data and accelerate classical machine learning tasks by taking the computational advantages of quantum systems. Simulation results on the MNIST data set show that the model has strong learning ability and good generalization performance.

AB - Quantum neural networks have provided entirely new insight into the future of artificial intelligence by combining the advantages of quantum computing technologies and classical neural network models. In this paper, a parameterized quantum circuit based quantum convolutional neural network model is proposed, which can deal with both Euclidean data and non-Euclidean data and accelerate classical machine learning tasks by taking the computational advantages of quantum systems. Simulation results on the MNIST data set show that the model has strong learning ability and good generalization performance.

KW - Quantum convolutional neural network

KW - Quantum graph convolutional neural network

KW - Quantum machine learning

KW - Quantum neural network

UR - https://www.scopus.com/pages/publications/85121869542

U2 - 10.7641/CTA.2021.10786

DO - 10.7641/CTA.2021.10786

M3 - 文章

AN - SCOPUS:85121869542

SN - 1000-8152

VL - 38

SP - 1772

EP - 1784

JO - Kongzhi Lilun Yu Yingyong/Control Theory and Applications

JF - Kongzhi Lilun Yu Yingyong/Control Theory and Applications

IS - 11

ER -

基于参数化量子电路的量子卷积神经网络模型及应用

Abstract

Access to Document

Other files and links

Fingerprint

Cite this