首页|Analysis of learnability of a novel hybrid quantum-classical convolutional neural network in image classification

Analysis of learnability of a novel hybrid quantum-classical convolutional neural network in image classification

扫码查看
原文链接
  • 万方数据
  • 维普
We design a new hybrid quantum-classical convolutional neural network(HQCCNN)model based on parameter quantum circuits.In this model,we use parameterized quantum circuits(PQCs)to redesign the convolutional layer in classical convolutional neural networks,forming a new quantum convolutional layer to achieve unitary transformation of quantum states,enabling the model to more accurately extract hidden information from images.At the same time,we combine the classical fully connected layer with PQCs to form a new hybrid quantum-classical fully connected layer to further improve the accuracy of classification.Finally,we use the MNIST dataset to test the potential of the HQCCNN.The results indicate that the HQCCNN has good performance in solving classification problems.In binary classification tasks,the classification accuracy of numbers 5 and 7 is as high as 99.71％.In multivariate classification,the accuracy rate also reaches 98.51％.Finally,we compare the performance of the HQCCNN with other models and find that the HQCCNN has better classification performance and convergence speed.

parameterized quantum circuitsquantum machine learninghybrid quantum-classical convolu-tional neural network

程涛、赵润盛、王爽、王睿、马鸿洋

展开 >

School of Information and Control Engineering,Qingdao University of Technology,Qingdao 266033,China

School of Sciences,Qingdao University of Technology,Qingdao 266033,China

山东省自然科学基金Joint Fund of Natural Science Foundation of Shandong ProvinceJoint Fund of Natural Science Foundation of Shandong Province

ZR2021MF049ZR2022LLZ012ZR2021LLZ001

2024

10.1088/1674-1056/ad1926

中国物理B(英文版)
中国物理学会和中国科学院物理研究所

中国物理B(英文版)

CSTPCDEI
影响因子：0.995
ISSN：1674-1056
年,卷(期)：2024.33(4)
  • 54