基于粒子群优化算法的量子卷积神经网络

doi:10.3969/j.issn.1007-5461.2025.01.012

量子电子学报 ›› 2025, Vol. 42 ›› Issue (1): 123-0.doi: 10.3969/j.issn.1007-5461.2025.01.012

基于粒子群优化算法的量子卷积神经网络

张嘉雯 1, 蔡彬彬 1,2, 林崧 1*

1 福建师范大学计算机与网络空间安全学院, 福建福州 350007; 2 数字福建环境监测物联网实验室, 福建福州 350007

收稿日期:2024-02-28 修回日期:2024-04-28 出版日期:2025-01-28 发布日期:2025-01-28
通讯作者: E-mail: lins95@fjnu.edu.cn E-mail:E-mail: lins95@fjnu.edu.cn
作者简介:张嘉雯 ( 2000 - ), 女, 福建龙岩人, 硕士, 主要从事量子机器学习的研究。E-mail: gamung123@163.com
基金资助:
国家自然科学基金 (62171131, 61976053), 福建省高等学校新世纪优秀人才支持计划 (2022J01186), 福建省自然科学基金项目 (2023J01533)

Quantum convolutional neural network based on particle swarm optimization algorithm

ZHANG Jiawen 1 , CAI Binbin 1,2 , LIN Song 1*

1 College of Computer and Cyber Security, Fujian Normal University, Fuzhou 350007, China; 2 Digital Fujian Internet-of-Things Laboratory of Environmental Monitoring, Fuzhou 350007, China

Received:2024-02-28 Revised:2024-04-28 Published:2025-01-28 Online:2025-01-28

摘要/Abstract

摘要： 针对当前量子卷积神经网络模型中参数化量子电路缺乏自适应目标选择策略的问题, 提出了一种基于粒子群优化算法自动优化电路的量子卷积神经网络模型。该模型通过将量子电路编码为粒子, 并利用粒子群优化算法对电路进行优化, 从而搜索出在图像分类任务上表现优异的电路结构。基于Fashion MNIST和MNIST标准数据集的仿真实验表明, 该模型具有较强的学习能力和良好的泛化性能, 准确率分别可达94.7%和99.05%。相较于现有量子卷积神经网络模型, 平均分类精度最高分别提升了4.14%和1.43%。

关键词: 量子光学, 量子卷积神经网络, 粒子群优化算法, 量子机器学习, 参数化量子电路

Abstract: Aiming at the lack of adaptive target selection strategy for parameterized quantum circuits in current quantum convolutional neural network models, a quantum convolutional neural network model based on the particle swarm optimization algorithm is proposed to optimize circuits automatically. The model optimizes quantum circuits by encoding the quantum circuits as particles, then uses the particle swarm optimization algorithm to search for the circuit architectures that performs well in image classification tasks. Stimulation experiments based on Fashion MNIST and MNIST datasets show that the model has strong learning ability and good generalization performance, with accuracy up to 94.7% and 99.05%, respectively. Compared to current quantum convolutional neural network models, the average classification accuracy is improved by 4.14% and 1.43% to the maximum, respectively.

Key words: quantum optics, quantum convolutional neural network, particle swarm optimization algorithm, quantum machine learning, parameterized quantum circuit

中图分类号:

TP319

张嘉雯, 蔡彬彬, 林崧 . 基于粒子群优化算法的量子卷积神经网络[J]. 量子电子学报, 2025, 42(1): 123-0.

ZHANG Jiawen , CAI Binbin , , LIN Song . Quantum convolutional neural network based on particle swarm optimization algorithm[J]. Chinese Journal of Quantum Electronics, 2025, 42(1): 123-0.

参考文献

[1] Krizhevsky A, Sutskever I, Hinton G E. Imagenet classification with deep convolutional neural networks[J]. Advances in neural information processing systems, 2012, 25.
[2] Simonyan K, Zisserman A. Very deep convolutional networks for large-scale image recognition[J]. arXiv preprint arXiv:1409.1556, 2014.
[3] Szegedy C, Liu W, Jia Y, et al. Going deeper with convolutions[C]//Proceedings of the IEEE conference on computer vision and pattern recognition. 2015: 1-9.
[4] He K, Zhang X, Ren S, et al. Deep residual learning for image recognition[C]//Proceedings of the IEEE conference on computer vision and pattern recognition. 2016: 770-778.
[5] LeCun Y, Bottou L, Bengio Y, et al. Gradient-based learning applied to document recognition[J]. Proceedings of the IEEE, 1998, 86(11): 2278-2324.
[6] Li Y C, Zhou R G, Xu R Q, et al. A quantum deep convolutional neural network for image recognition[J]. Quantum Science and Technology, 2020, 5(4): 044003.
[7] Wei S J, Chen Y H, Zhou Z R, et al. A quantum convolutional neural network on NISQ devices[J]. AAPPS Bulletin, 2022, 32: 1-11.
[8] Chen G, Chen Q, Long S, et al. Quantum convolutional neural network for image classification[J]. Pattern Analysis and Applications, 2023, 26(2): 655-667.
[9] Pesah A, Cerezo M, Wang S, et al. Absence of barren plateaus in quantum convolutional neural networks[J]. Physical Review X, 2021, 11(4): 041011.
[10] 范兴奎, 刘广哲, 王浩文等. 基于量子卷积神经网络的图像识别新模型[J]. 电子科技大学学报, 2022, 51(05): 642-650.
[11] Cong I, Choi S, Lukin M D. Quantum convolutional neural networks[J]. Nature Physics, 2019, 15(12): 1273-1278.
[12] Henderson M, Shakya S, Pradhan S, et al. Quanvolutional neural networks: powering image recognition with quantum circuits[J]. Quantum Machine Intelligence, 2020, 2(1): 2.
[13] Hur T, Kim L, Park D K. Quantum convolutional neural network for classical data classification[J]. Quantum Machine Intelligence, 2022, 4(1): 3.
[14] Liu J, Lim K H, Wood K L, et al. Hybrid quantum-classical convolutional neural networks[J]. Science China Physics, Mechanics & Astronomy, 2021, 64(9): 290311.
[15] Ruiz-Perez L, Garcia-Escartin J C. Quantum arithmetic with the quantum Fourier transform[J]. Quantum Information Processing, 2017, 16: 1-14.
[16] Yao X W, Wang H, Liao Z, et al. Quantum image processing and its application to edge detection: theory and experiment[J]. Physical Review X, 2017, 7(3): 031041.
[17] 臧一鸣, 朱尚超, 魏战红等. 一种量子图像伪彩色编码方法[J]. 量子电子学报, 2022, 39(3): 343.
[18] 杨光, 钞苏亚, 聂敏等. 面向图像分类的混合量子长短期记忆神经网络构建方法[J]. 物理学报, 2023, 72(05): 474-487.
[19] 吕颜轩, 高庆, 吕金虎等. 面向近期量子处理器的量子神经网络研究进展[J]. 中国科学: 技术科学, 2022, 52(04): 547-564.
[20] Cerezo M, Arrasmith A, Babbush R, et al. Variational quantum algorithms[J]. Nature Reviews Physics, 2021, 3(9): 625-644.
[21] Huang H L, Xu X Y, Guo C, et al. Near-term quantum computing techniques: Variational quantum algorithms, error mitigation, circuit compilation, benchmarking and classical simulation[J]. Science China Physics, Mechanics & Astronomy, 2023, 66(5): 250302.
[22] Bharti K, Cervera-Lierta A, Kyaw T H, et al. Noisy intermediate-scale quantum algorithms[J]. Reviews of Modern Physics, 2022, 94(1): 015004.
[23] Kennedy J, Eberhart R. Particle swarm optimization[C]//Proceedings of ICNN'95-international conference on neural networks. IEEE, 1995, 4: 1942-1948.
[24] Benedetti M, Lloyd E, Sack S, et al. Parameterized quantum circuits as machine learning models[J]. Quantum Science and Technology, 2019, 4(4): 043001.
[25] Ruder S. An overview of gradient descent optimization algorithms[J]. arXiv preprint arXiv:1609.04747, 2016.
[26] Schuld M, Bergholm V, Gogolin C, et al. Evaluating analytic gradients on quantum hardware[J]. Physical Review A, 2019, 99(3): 032331.
[27] Crooks G E. Gradients of parameterized quantum gates using the parameter-shift rule and gate decomposition[J]. arXiv preprint arXiv:1905.13311, 2019.
[28] Mari A, Bromley T R, Killoran N. Estimating the gradient and higher-order derivatives on quantum hardware[J]. Physical Review A, 2021, 103(1): 012405.
[29] Bergholm, V. et al. Pennylane: Automatic differentiation of hybrid quantum–classical computations. Preprint at https://arxiv.org/abs/1811.04968 (2018).
[30] Nesterov Y E. A method of solving a convex programming problem with convergence rate O(1/k2)[C]//Doklady Akademii Nauk. Russian Academy of Sciences, 1983, 269(3): 543-547.
[31] 吴琼, 马雷. 一种基于 LoG 算子的量子图像边缘检测算法[J]. 量子电子学报, 2022, 39(5): 720.
[32] Sharma K, Khatri S, Cerezo M, et al. Noise resilience of variational quantum compiling[J]. New Journal of Physics, 2020, 22(4): 043006.
[33] Cincio L, Rudinger K, Sarovar M, et al. Machine learning of noise-resilient quantum circuits[J]. PRX Quantum, 2021, 2(1): 010324.
[34] Zhang Y H, Zheng P L, Zhang Y, et al. Topological quantum compiling with reinforcement learning[J]. Physical Review Letters, 2020, 125(17): 170501.
[35] He Z, Li L, Zheng S, et al. Variational quantum compiling with double Q-learning[J]. New Journal of Physics, 2021, 23(3): 033002.
[36] Kuo E J, Fang Y L L, Chen S Y C. Quantum architecture search via deep reinforcement learning[J]. arXiv preprint arXiv:2104.07715, 2021.
[37] Ostaszewski M, Trenkwalder L M, Masarczyk W, et al. Reinforcement learning for optimization of variational quantum circuit architectures[J]. Advances in Neural Information Processing Systems, 2021, 34: 18182-18194.

基于粒子群优化算法的量子卷积神经网络

Quantum convolutional neural network based on particle swarm optimization algorithm

PDF

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 15

编辑推荐

Metrics

本文评价

[1]	王国翠 , 林志 , 李曦坤 , 杨青 , 杨名 . 基于光量子行走的多体量子纠缠纯态克隆方案[J]. 量子电子学报, 2025, 42(2): 206-216.
[2]	蒙雅. 光波导中的一维拓扑无硬币态量子行走[J]. 量子电子学报, 2025, 42(2): 217-228.
[3]	郑亮 , 刘超 , 周宗权 , 李传锋 , . 基于晶体光波导的长寿命光存储[J]. 量子电子学报, 2025, 42(2): 246-259.
[4]	谭心 , 贺占清 , 杨桥 , 王健 , 苍磊 , 杜岩龙 , 祁晖 , . 金刚石纳米柱增强色心荧光收集效率研究[J]. 量子电子学报, 2025, 42(2): 255-264.
[5]	王婷 , 穆青霞 . 高保真度声子-光子量子隐形传态[J]. 量子电子学报, 2025, 42(1): 100-0.
[6]	陆叶锴 , 白恩健 , 蒋学芹 , 吴贇 , 陈根龙 . 基于元胞自动机的高速保密增强算法FPGA 实现[J]. 量子电子学报, 2025, 42(1): 111-0.
[7]	郭海琳, 孙东云, 刘昊鑫, 张翠玲, 杨哲, 张存林, . 太赫兹量子通信 (特邀, 封面文章）[J]. 量子电子学报, 2025, 42(1): 1-0.
[8]	陆文皓 #, 吴梓涵 #, 马均瑶 , 余杨 , 赵生妹 . 免相位后选择双场量子密钥分发协议光源错误分析[J]. 量子电子学报, 2024, 41(6): 891-900.
[9]	徐小桐 , 石润华 , 柯唯阳 , 于辉. 无中心的量子匿名一票否决方案[J]. 量子电子学报, 2024, 41(6): 901-913.
[10]	夏长超 , 宋利伟 . 玻色-爱因斯坦凝聚体腔中完美光力诱导透明[J]. 量子电子学报, 2024, 41(6): 914-923.
[11]	王其兵 , 王林松 , 王雅琦 , 李力 , 许华醒 , 王少华 , . 一种基于 CMOS 的小型化量子随机数产生装置[J]. 量子电子学报, 2024, 41(6): 924-932.
[12]	沈威 , 刘尉悦. 时频域结合的量子通信时间同步方法[J]. 量子电子学报, 2024, 41(6): 933-941.
[13]	娄小平 , 范洲 , 戈启越 . 基于量子行走的量子指定验证者签名方案[J]. 量子电子学报, 2024, 41(6): 942-955.
[14]	刘文经 , 刘骏 , 曹原 , 王棚栎 , 张融 . 基于一维圆上量子行走的图片加密[J]. 量子电子学报, 2024, 41(6): 956-969.
[15]	张丹彤薛冬峰. 晶格工程电子态调控研究 (封面文章）[J]. 量子电子学报, 2024, 41(6): 839-851.