The Journal of China Universities of Posts and Telecommunications ›› 2022, Vol. 29 ›› Issue (4): 21-31.doi: 10.19682/j.cnki.1005-8885.2022.2016

• Special Topic: Quantum Science and Technology • Previous Articles     Next Articles

Quantum classifier with parameterized quantum circuit based on the isolated quantum system

Shi Jinjing, Wang Wenxuan, Xiao Zimeng, Mu Shuai, Li Qin   

  1. 1. School of Computer Science and Engineering, Central South University, Changsha 410083, China
    2. School of Computer Science and School of Cyberspace Science, Xiangtan University, Xiangtan 411301, China
  • Received:2022-04-28 Revised:2022-05-31 Accepted:2022-06-09 Online:2022-08-31 Published:2022-08-31
  • Contact: Mu Shuai, Li Qin, E-mails: csumushuai@csu.edu.cn, liqin@xtu.edu.cn E-mail:csumushuai@csu.edu.cn, liqin@xtu.edu.cn
  • Supported by:
    This work was supported by the National Natural Science Foundation of China (61972418, 61872390), the Natural
    Science Foundation of Hunan Province (2020JJ4750), the Special Foundation for Distinguished Young Scientists of
    Changsha (kq1905058), China Computer Federation (CCF) -Baidu Open Fund (CCF-BAIDUOF2021031), the Fundamental
    Research Funds for the Central Universities of Central South University, China (2022XQLH014).

Abstract: It is a critical challenge for quantum machine learning to classify the datasets accurately. This article develops a quantum classifier based on the isolated quantum system (QC-IQS) to classify nonlinear and multidimensional datasets. First, a model of QC-IQS is presented by creating parameterized quantum circuits (PQCs) based on the decomposing of unitary operators with the Hamiltonian in the isolated quantum system. Then, a parameterized quantum classification algorithm (QCA) is designed to calculate the classification results by updating the loss function until it converges. Finally, the experiments on nonlinear random number datasets and Iris datasets are designed to demonstrate that the QC-IQS model can handle and generate accurate classification results on different kinds of datasets. The experimental results reveal that the QC-IQS is adaptive and learnable to handle different types of data. Moreover, QC-IQS compensates the issue that the accuracy of previous quantum classifiers declines when dealing with diverse datasets. It promotes the process of novel data processing with quantum machine learning and has the potential for more comprehensive applications in the future.

Key words: quantum classifier, quantum classification, isolated quantum system, parameterized quantum circuit, Hamiltonian

CLC Number: