基于FRQI联合额外测量的多分类量子神经网络  

A quantum neural network for multi-classifications by using FRQI with extra measurement

作　　者：黄建军 王云江 程承坤[2] 王增斌 石莎 HUANG Jian-Jun;WANG Yun-Jiang;CHENG Cheng-Kun;WANG Zeng-Bin;SHI Sha(Guangzhou Institute of Technology,Xidian University,Guangzhou 510555,China;School of Telecommunications Engineering,Xidian University,Xi’an 710071,China;Hangzhou Institute of Technology,Xidian University,Hangzhou 311231,China;Quantah Systems Sci.&Tech.Stockholdings Ltd.,Beijing 100095,China)

机构地区：[1]西安电子科技大学广州研究院,广州510555 [2]西安电子科技大学通信工程学院,西安710071 [3]西安电子科技大学杭州研究院,杭州311231 [4]北京量子体系科技股份有限公司,北京100095

出　　处：《中国科学:物理学、力学、天文学》2025年第4期91-99,共9页Scientia Sinica Physica,Mechanica & Astronomica

基　　金：广东省自然科学基金(编号:2023A1515010671);陕西省重点研发计划(编号:2023-YBGY-206,2024GX-YBXM-069);陕西高校青年创新团队计划资助项目。

摘　　要：分类是量子机器学习的一个核心应用.本文针对当前纯量子分类器所存在的消耗量子比特数目多、在多分类任务上效果不尽如人意等问题,在量子图像的灵活表示(FRQI)的基础上,通过引入额外测量比特并将其与颜色量子比特位相连接,构造了一种可用于多分类任务的新型量子线路模型QCCE.该模型不仅继承了FRQI的编码优势,能用较少量子比特编码高维图像输入,同时所有可训练参数都在量子线路中,经典计算只提供损失函数和优化器.在MNIST以及Fashion MNIST等数据集上的实验表明,QCCE模型在三、四、五等多分类任务中,相比同类的HEA和MORE等量子线路模型在分类精度和收敛速度方面均展现出明显优势.本文的研究为量子机器学习在图像处理方面的应用提供了新思路和方法.Classification is a core application of quantum machine learning.This study aims at the problems existing in current pure quantum classifiers,such as the large number of consumed qubits and the unsatisfactory performance in multi-classification tasks.Based on the flexible representation of quantum images(FRQI),a new quantum circuit model QCCE that can be used for multi-classification tasks is constructed by introducing additional measurement qubits and connecting them to the color qubit bits.This model not only inherits the encoding advantages of FRQI,enabling it to encode high-dimensional image inputs with a relatively small number of qubits,but also has all trainable parameters in the quantum circuit,with classical computing only providing the loss function and optimizer.Experiments on datasets such as MNIST and Fashion MNIST have shown that in multi-classification tasks like three,four,and five-class classifications,the QCCE model demonstrates obvious advantages over similar quantum circuit models such as HEA and MORE in terms of classification accuracy and convergence speed.The research in this study provides new ideas and methods for the application of quantum machine learning in image processing.

关 键 词：量子计算 量子神经网络 多分类 量子线路 

分 类 号：TP183[自动化与计算机技术—控制理论与控制工程]