Multiclass classification using quantum convolutional neural networks with hybrid quantum-classical learning

被引:15
|
作者
Bokhan, Denis [1 ,2 ]
Mastiukova, Alena S. [2 ,3 ]
Boev, Aleksey S. [2 ]
Trubnikov, Dmitrii N. [1 ]
Fedorov, Aleksey K. [2 ,3 ]
机构
[1] Lomonosov Moscow State Univ, Dept Chem, Phys Chem Div, Lab Mol Beams, Moscow, Russia
[2] Russian Quantum Ctr, Moscow, Russia
[3] Natl Univ Sci & Technol MISIS, Moscow, Russia
来源
FRONTIERS IN PHYSICS | 2022年 / 10卷
基金
俄罗斯科学基金会;
关键词
quantum learning; multinomial classification; paramaterized quantum circuit; variational circuits; amplitude encoding; POWER;
D O I
10.3389/fphy.2022.1069985
中图分类号
O4 [物理学];
学科分类号
0702 ;
摘要
Multiclass classification is of great interest for various applications, for example, it is a common task in computer vision, where one needs to categorize an image into three or more classes. Here we propose a quantum machine learning approach based on quantum convolutional neural networks for solving the multiclass classification problem. The corresponding learning procedure is implemented via TensorFlowQuantum as a hybrid quantum-classical (variational) model, where quantum output results are fed to the softmax activation function with the subsequent minimization of the cross entropy loss via optimizing the parameters of the quantum circuit. Our conceptional improvements here include a new model for a quantum perceptron and an optimized structure of the quantum circuit. We use the proposed approach to solve a 4-class classification problem for the case of the MNIST dataset using eight qubits for data encoding and four ancilla qubits; previous results have been obtained for 3-class classification problems. Our results show that accuracies of our solution are similar to classical convolutional neural networks with comparable numbers of trainable parameters. We expect that our finding provide a new step towards the use of quantum neural networks for solving relevant problems in the NISQ era and beyond.
引用
收藏
页数:9
相关论文
共 50 条
  • [1] Multiclass classification using quantum convolutional neural networks with hybrid quantum-classical learning (vol 10, 1069985, 2022)
    Bokhan, Denis
    Mastiukova, Alena S. S.
    Boev, Aleksey S. S.
    Trubnikov, Dmitrii N. N.
    Fedorov, Aleksey K. K.
    [J]. FRONTIERS IN PHYSICS, 2023, 10
  • [2] Hybrid quantum-classical convolutional neural networks
    Junhua Liu
    Kwan Hui Lim
    Kristin L.Wood
    Wei Huang
    Chu Guo
    He-Liang Huang
    [J]. Science China(Physics,Mechanics & Astronomy), 2021, 64 (09) : 5 - 12
  • [3] Hybrid quantum-classical convolutional neural networks
    Liu, Junhua
    Lim, Kwan Hui
    Wood, Kristin L.
    Huang, Wei
    Guo, Chu
    Huang, He-Liang
    [J]. SCIENCE CHINA-PHYSICS MECHANICS & ASTRONOMY, 2021, 64 (09)
  • [4] Hybrid quantum-classical convolutional neural networks
    Junhua Liu
    Kwan Hui Lim
    Kristin L. Wood
    Wei Huang
    Chu Guo
    He-Liang Huang
    [J]. Science China Physics, Mechanics & Astronomy, 2021, 64
  • [5] Hybrid quantum-classical convolutional neural networks with privacy quantum computing
    Huang, Siwei
    Chang, Yan
    Lin, Yusheng
    Zhang, Shibin
    [J]. QUANTUM SCIENCE AND TECHNOLOGY, 2023, 8 (02)
  • [6] Hybrid quantum-classical convolutional neural network for phytoplankton classification
    Shi, Shangshang
    Wang, Zhimin
    Shang, Ruimin
    Li, Yanan
    Li, Jiaxin
    Zhong, Guoqiang
    Gu, Yongjian
    [J]. FRONTIERS IN MARINE SCIENCE, 2023, 10
  • [7] Quantum-classical convolutional neural networks in radiological image classification
    Matic, Andrea
    Monnet, Maureen
    Lorenz, Jeanette Miriam
    Schachtner, Balthasar
    Messerer, Thomas
    [J]. 2022 IEEE INTERNATIONAL CONFERENCE ON QUANTUM COMPUTING AND ENGINEERING (QCE 2022), 2022, : 56 - 66
  • [8] Embedding Learning in Hybrid Quantum-Classical Neural Networks
    Liu, Minzhao
    Liu, Junyu
    Liu, Rui
    Makhanov, Henry
    Lykov, Danylo
    Apte, Anuj
    Alexeev, Yuri
    [J]. 2022 IEEE INTERNATIONAL CONFERENCE ON QUANTUM COMPUTING AND ENGINEERING (QCE 2022), 2022, : 79 - 86
  • [9] Hybrid Quantum-Classical Neural Networks
    Arthur, Davis
    Date, Prasanna
    [J]. 2022 IEEE INTERNATIONAL CONFERENCE ON QUANTUM COMPUTING AND ENGINEERING (QCE 2022), 2022, : 49 - 55
  • [10] Hybrid Quantum-Classical Convolutional Neural Network Model for Image Classification
    Fan, Fan
    Shi, Yilei
    Guggemos, Tobias
    Zhu, Xiao Xiang
    [J]. IEEE Transactions on Neural Networks and Learning Systems, 2024, 35 (12) : 18145 - 18159