搜索

x

留言板

尊敬的读者、作者、审稿人, 关于本刊的投稿、审稿、编辑和出版的任何问题, 您可以本页添加留言。我们将尽快给您答复。谢谢您的支持!

姓名
邮箱
手机号码
标题
留言内容
验证码

面向图像分类的混合量子长短期记忆神经网络构建方法

杨光 钞苏亚 聂敏 刘原华 张美玲

引用本文:
Citation:

面向图像分类的混合量子长短期记忆神经网络构建方法

杨光, 钞苏亚, 聂敏, 刘原华, 张美玲

Construction method of hybrid quantum long-short term memory neural network for image classification

Yang Guang, Chao Su-Ya, Nie Min, Liu Yuan-Hua, Zhang Mei-Ling
PDF
HTML
导出引用
  • 长短期记忆(long-short term memory, LSTM)神经网络通过引入记忆单元来解决长期依赖、梯度消失和梯度爆炸问题, 广泛应用于时间序列分析与预测. 将量子计算与LSTM神经网络结合将有助于提高其计算效率并降低模型参数个数, 从而显著改善传统LSTM神经网络的性能. 本文提出一种可用于图像分类的混合量子LSTM (hybrid quantum LSTM, HQLSTM)网络模型, 利用变分量子电路代替经典LSTM网络中的神经细胞, 以实现量子网络记忆功能, 同时引入Choquet离散积分算子来增强数据之间的聚合程度. HQLSTM网络中的记忆细胞由多个可实现不同功能的变分量子电路(variation quantum circuit, VQC)构成, 每个VQC由三部分组成: 编码层利用角度编码降低网络模型设计的复杂度; 变分层采用量子自然梯度优化算法进行设计, 使得梯度下降方向不以特定参数为目标, 从而优化参数更新过程, 提升网络模型的泛化性和收敛速度; 测量层利用泡利 Z 门进行测量, 并将测量结果的期望值输入到下一层实现对量子电路中有用信息的提取. 在MNIST, FASHION-MNIST和CIFAR数据集上的图像分类实验结果表明, 与经典LSTM、量子LSTM相比, HQLSTM模型获得了较高的图片分类精度和较低的损失值. 同时, HQLSTM、量子LSTM网络空间复杂度相较于经典的LSTM网络实现了明显的降低.
    Long-short term memory (LSTM) neural network solves the problems of long-term dependence, gradient disappearance and gradient explosion by introducing memory units, and is widely used in time series analysis and prediction. Combining quantum computing with LSTM neural network will help to improve its computational efficiency and reduce the number of model parameters, thus significantly improving the performance of traditional LSTM neural network. This paper proposes a hybrid quantum LSTM (hybrid quantum long-short term memory, HQLSTM) network model that can be used to realize the image classification. It uses variable quantum circuits to replace the nerve cells in the classical LSTM network to realize the memory function of the quantum network. At the same time, it introduces Choquet integral operator to enhance the degree of aggregation between data. The memory cells in the HQLSTM network are composed of multiple variation quantum circuits (VQC) that can realize different functions. Each VQC consists of three parts: the coding layer, which uses angle coding to reduce the complexity of network model design; the variation layer, which is designed with quantum natural gradient optimization algorithm, so that the gradient descent direction does not target specific parameters, thereby optimizing the parameter update process and improving the generalization and convergence speed of the network model; the measurement layer, which uses the Pauli Z gate to measure, and the expected value of the measurement result is input to the next layer to extract useful information from the quantum circuit. The experimental results on the MNIST, FASHION-MNIST and CIFAR datasets show that the HQLSTM model achieves higher image classification accuracy and lower loss value than the classical LSTM model and quantum LSTM model. At the same time, the network space complexity of HQLSTM and quantum LSTM are significantly reduced compared with the classical LSTM network.
      通信作者: 钞苏亚, 1920464642@qq.com
    • 基金项目: 国家自然科学基金(批准号: 61971348, 61201194)和陕西省自然科学基础研究计划(批准号: 2021JM-464)资助的课题
      Corresponding author: Chao Su-Ya, 1920464642@qq.com
    • Funds: Project supported by the National Natural Science Foundation of China (Grant Nos. 61971348, 61201194) and the Natural Science Basic Research Program of Shaanxi province, China (Grant No. 2021JM-464)
    [1]

    Acharya U R, Oh S L, Hagiwara Y, HongTan J, Adam M, Gertych A, Tan R S 2017 Comput. Biol. Med. 89 389Google Scholar

    [2]

    Hage S R, Nieder A 2016 Trends Neurosci. 39 813Google Scholar

    [3]

    Xu S, Liu K, Li X G 2019 Neurocomputing 335 1Google Scholar

    [4]

    Zhao J, Yang S P, Li Q, Liu Y Q, Gu X H, Liu W P 2021 Measurement 176 109088Google Scholar

    [5]

    Feng X C, Qin B, Liu T 2018 Sci. China Inf. Sci. 61 092106Google Scholar

    [6]

    Tsai S T, Kuo E J, Tiwary P 2020 Nat. Commun. 11 5115Google Scholar

    [7]

    Yadav S S, Jadhav S M 2019 J. Big Data 6 96Google Scholar

    [8]

    Yan R, Ren F, Wang Z H, Wang L H, Zhang T, Liu Y D, Rao X S, Zheng C H, Zhang F 2020 Methods 173 52Google Scholar

    [9]

    Xin M, Wang Y 2019 EURASIP J. Image Video Process. 2019 40Google Scholar

    [10]

    Steane A 1998 Rep. Prog. Phys. 61 117Google Scholar

    [11]

    Gyongyosi L, Imre S 2019 Comput. Sci. Rev. 31 51Google Scholar

    [12]

    Egger D J, Gambella C, Marecek J, McFaddin S, Mevissen M, Raymond R, Simonetto A, Woerner S, Yndurain E 2020 IEEE Trans. Quantum Eng. 1 3101724Google Scholar

    [13]

    Wu N, Song F M 2007 Front. Comput. Sci. 1 1Google Scholar

    [14]

    He K Y, Geng X, Huang R T, Liu J S, Chen W 2021 Chin. Phys. B 30 080304Google Scholar

    [15]

    Harrow A W, Hassidim A, Lloyd S 2009 Phys. Rev. Lett. 103 150502Google Scholar

    [16]

    Grover L K 2005 Phys. Rev. Lett. 95 150501Google Scholar

    [17]

    Yoder T J, Low G H, Chuang I L 2014 Phys. Rev. Lett. 113 210501Google Scholar

    [18]

    Kouda N, Matsui N, Nishimura H, Peper F 2005 Neural Comput. Appl. 14 114Google Scholar

    [19]

    Li P C, Xiao H, Shang F H, Tong X F, Li X, Cao M J 2013 Neurocomputing 117 81Google Scholar

    [20]

    Li P C, Xiao H 2013 Neural Process. Lett. 40 143

    [21]

    Zhou R G, Ding Q L 2007 Int. J. Theor. Phys. 46 3209Google Scholar

    [22]

    Cong I, Choi S, Lukin M D 2019 Nat. Phys. 15 1273Google Scholar

    [23]

    Henderson M, Shakya S, Pradhan S, Cook T 2020 Quantum Mach. Intell. 2 1Google Scholar

    [24]

    Niu X F, Ma W P 2021 Laser Phys. Lett. 18 025201Google Scholar

    [25]

    Houssein E H, Abohashima Z, Elhoseny M, Mohamed W M 2022 J. Comput. Des. Eng. 9 343

    [26]

    Hur T, Kim L, Park D K 2022 Quantum Mach. Intell. 4 1Google Scholar

    [27]

    Chen G M, Chen Q, Long S, Zhu W H, Yuan Z D, Wu Y L 2022 Pattern Anal. Applic. 25 1Google Scholar

    [28]

    Xia R, Kais S 2020 Entropy 22 828Google Scholar

    [29]

    Mari A, Bromley T R, Izaac J, Schuld M, Killoran N 2020 Quantum 4 340Google Scholar

    [30]

    Yu Y, Si X S, Hu C H, Zhang J X 2019 Neural Comput. 31 1235Google Scholar

    [31]

    Shewalkar A 2019 J. Artif. Intell. Soft 9 235

    [32]

    Hua Y, Mou L, Zhu X X 2019 ISPRS J. Photogramm. Remote Sens. 149 188Google Scholar

    [33]

    Takáč Z, Ferrero-Jaurrieta M, Horanská Ľ, Krivoňáková N, Dimuro G. P, Bustince H 2021 2021 International Conference on Electrical, Computer and Energy Technologies (ICECET) Malaysia, Kuala Lumpur, June 12–13, 2021 p1

    [34]

    Ma A, Filippi A. M, Wang Z, Yin Z 2019 Remote Sens. 11 194Google Scholar

    [35]

    Chen S Y C, Yoo S, Fang Y L L 2022 2022 IEEE International Conference on Acoustics, Speech and Signal Processing Singapore May 22–27, 2022 p8622

    [36]

    Stokes J, Izaac J, Killoran N, Carleo G 2020 Quantum 4 269Google Scholar

    [37]

    Wiebe N 2020 New J. Phys. 22 091001Google Scholar

    [38]

    Wei S J, Chen Y H, Zhou Z R, Long G L 2022 AAPPS Bull. 32 1Google Scholar

    [39]

    赵娅, 郭嘉慧, 李盼池 2021 电子与信息学报 43 204Google Scholar

    Zhao Y, Guo J H, Li P C 2021 J. Electron. Inf. Techn. 43 204Google Scholar

    [40]

    Watson T F, Philips S G J, Kawakami E, Ward D R, Scarlino P, Veldhorst M, Savage D E, Lagally M G, Friesen M, Coppersmith S N, Eriksson M A, Vandersypen L M K 2018 Nature 555 633Google Scholar

    [41]

    Chew Y, Tomita T, Mahesh T P, Sugawa S, Léséleuc S D, Ohmori K 2022 Nat. Photonics. 16 724Google Scholar

    [42]

    杨靖北, 丛爽, 陈鼎 2017 控制理论与应用 34 15144Google Scholar

    Yang J B, Cong S, Chen D 2017 J. Control Theory Appl. 34 15144Google Scholar

    [43]

    Gokhale P, Angiuli O, Ding Y, Gui K, Tomesh T, Suchara M, Martonosi M, Chong F T 2020 IEEE Trans. Quantum Eng. 1 1Google Scholar

    [44]

    Huang H Y, Kueng R, Preskill J 2021 Phys. Rev. Lett. 126 190505Google Scholar

  • 图 1  LSTM网络模型结构

    Fig. 1.  The structure of the LSTM network model.

    图 2  二维的Choquet离散积分算子图示

    Fig. 2.  Two-dimensional Choquet discrete integral operator diagram.

    图 3  HQLSTM网络模型结构

    Fig. 3.  The structure of the HQLSTM network model.

    图 4  HQLSTM细胞中的VQC结构

    Fig. 4.  The overall structure of the HQLSTM network model.

    图 5  计算Fubini-Study度量张量的部分VQC结构

    Fig. 5.  Calculate part of the VQC structure of the Fubini-Study metric tensor.

    图 6  数据集样本 (a) MNIST数据集; (b) FASHION-MNIST数据集; (c) CIFAR数据集

    Fig. 6.  Dataset image samples: (a) MNIST dataset; (b) FASHION_MNIST dataset; (c) CIFAR dataset.

    图 7  MNIST数据集 (a)分类精度对比; (b)损失函数值对比

    Fig. 7.  MNIST dataset: (a) Comparison of classification accuracy; (b) comparison of loss value.

    图 8  不同优化算法损失值对比

    Fig. 8.  Comparison of loss values ​​of different optimization algorithms.

    图 9  FASHION-MNIST数据集 (a) 分类精度对比; (b) 损失函数值对比

    Fig. 9.  FASHION-MNIST dataset: (a) Comparison of classification accuracy; (b) comparison of loss value

    图 10  不同优化算法损失值对比

    Fig. 10.  Comparison of loss values ​​of different optimization algorithms.

    图 11  CIFAR彩色数据集 (a)分类精度对比; (b)损失函数值对比

    Fig. 11.  CIFAR color dataset: (a) Classification accuracy; (b) comparison of loss value.

    表 1  LSTM网络模型参数

    Table 1.  LSTM network model parameters.

    参数数量
    Input_size4
    Hidden_size4
    Time_step49
    Dropout比率0.15
    Batch128
    网络层数2
    输出节点数10
    学习率0.001
    下载: 导出CSV

    表 2  QLSTM和HQLSTM网络模型参数

    Table 2.  QLSTM and HQLSTM network model parameters.

    参数数量
    输入量子比特数4
    Hidden_size4
    Time_step49
    Dropout比率0.15
    Batch128
    网络层数2
    输出节点数10
    学习率0.001
    下载: 导出CSV

    表 3  不同网络模型图像分类精度比较

    Table 3.  Comparison of image classification accuracy of different network models.

    网络模型数据集类别总数分类精度/%
    Ref. [35]MNIST1097.894
    FASHION-MNIST1096.865
    CIFAR1096.334
    HQLSTMMNIST1099.154
    FASHION-MNIST1098.273
    CIFAR1098.631
    经典LSTMMNIST1097.306
    FASHION-MNIST1096.829
    CIFAR1092.671
    下载: 导出CSV
  • [1]

    Acharya U R, Oh S L, Hagiwara Y, HongTan J, Adam M, Gertych A, Tan R S 2017 Comput. Biol. Med. 89 389Google Scholar

    [2]

    Hage S R, Nieder A 2016 Trends Neurosci. 39 813Google Scholar

    [3]

    Xu S, Liu K, Li X G 2019 Neurocomputing 335 1Google Scholar

    [4]

    Zhao J, Yang S P, Li Q, Liu Y Q, Gu X H, Liu W P 2021 Measurement 176 109088Google Scholar

    [5]

    Feng X C, Qin B, Liu T 2018 Sci. China Inf. Sci. 61 092106Google Scholar

    [6]

    Tsai S T, Kuo E J, Tiwary P 2020 Nat. Commun. 11 5115Google Scholar

    [7]

    Yadav S S, Jadhav S M 2019 J. Big Data 6 96Google Scholar

    [8]

    Yan R, Ren F, Wang Z H, Wang L H, Zhang T, Liu Y D, Rao X S, Zheng C H, Zhang F 2020 Methods 173 52Google Scholar

    [9]

    Xin M, Wang Y 2019 EURASIP J. Image Video Process. 2019 40Google Scholar

    [10]

    Steane A 1998 Rep. Prog. Phys. 61 117Google Scholar

    [11]

    Gyongyosi L, Imre S 2019 Comput. Sci. Rev. 31 51Google Scholar

    [12]

    Egger D J, Gambella C, Marecek J, McFaddin S, Mevissen M, Raymond R, Simonetto A, Woerner S, Yndurain E 2020 IEEE Trans. Quantum Eng. 1 3101724Google Scholar

    [13]

    Wu N, Song F M 2007 Front. Comput. Sci. 1 1Google Scholar

    [14]

    He K Y, Geng X, Huang R T, Liu J S, Chen W 2021 Chin. Phys. B 30 080304Google Scholar

    [15]

    Harrow A W, Hassidim A, Lloyd S 2009 Phys. Rev. Lett. 103 150502Google Scholar

    [16]

    Grover L K 2005 Phys. Rev. Lett. 95 150501Google Scholar

    [17]

    Yoder T J, Low G H, Chuang I L 2014 Phys. Rev. Lett. 113 210501Google Scholar

    [18]

    Kouda N, Matsui N, Nishimura H, Peper F 2005 Neural Comput. Appl. 14 114Google Scholar

    [19]

    Li P C, Xiao H, Shang F H, Tong X F, Li X, Cao M J 2013 Neurocomputing 117 81Google Scholar

    [20]

    Li P C, Xiao H 2013 Neural Process. Lett. 40 143

    [21]

    Zhou R G, Ding Q L 2007 Int. J. Theor. Phys. 46 3209Google Scholar

    [22]

    Cong I, Choi S, Lukin M D 2019 Nat. Phys. 15 1273Google Scholar

    [23]

    Henderson M, Shakya S, Pradhan S, Cook T 2020 Quantum Mach. Intell. 2 1Google Scholar

    [24]

    Niu X F, Ma W P 2021 Laser Phys. Lett. 18 025201Google Scholar

    [25]

    Houssein E H, Abohashima Z, Elhoseny M, Mohamed W M 2022 J. Comput. Des. Eng. 9 343

    [26]

    Hur T, Kim L, Park D K 2022 Quantum Mach. Intell. 4 1Google Scholar

    [27]

    Chen G M, Chen Q, Long S, Zhu W H, Yuan Z D, Wu Y L 2022 Pattern Anal. Applic. 25 1Google Scholar

    [28]

    Xia R, Kais S 2020 Entropy 22 828Google Scholar

    [29]

    Mari A, Bromley T R, Izaac J, Schuld M, Killoran N 2020 Quantum 4 340Google Scholar

    [30]

    Yu Y, Si X S, Hu C H, Zhang J X 2019 Neural Comput. 31 1235Google Scholar

    [31]

    Shewalkar A 2019 J. Artif. Intell. Soft 9 235

    [32]

    Hua Y, Mou L, Zhu X X 2019 ISPRS J. Photogramm. Remote Sens. 149 188Google Scholar

    [33]

    Takáč Z, Ferrero-Jaurrieta M, Horanská Ľ, Krivoňáková N, Dimuro G. P, Bustince H 2021 2021 International Conference on Electrical, Computer and Energy Technologies (ICECET) Malaysia, Kuala Lumpur, June 12–13, 2021 p1

    [34]

    Ma A, Filippi A. M, Wang Z, Yin Z 2019 Remote Sens. 11 194Google Scholar

    [35]

    Chen S Y C, Yoo S, Fang Y L L 2022 2022 IEEE International Conference on Acoustics, Speech and Signal Processing Singapore May 22–27, 2022 p8622

    [36]

    Stokes J, Izaac J, Killoran N, Carleo G 2020 Quantum 4 269Google Scholar

    [37]

    Wiebe N 2020 New J. Phys. 22 091001Google Scholar

    [38]

    Wei S J, Chen Y H, Zhou Z R, Long G L 2022 AAPPS Bull. 32 1Google Scholar

    [39]

    赵娅, 郭嘉慧, 李盼池 2021 电子与信息学报 43 204Google Scholar

    Zhao Y, Guo J H, Li P C 2021 J. Electron. Inf. Techn. 43 204Google Scholar

    [40]

    Watson T F, Philips S G J, Kawakami E, Ward D R, Scarlino P, Veldhorst M, Savage D E, Lagally M G, Friesen M, Coppersmith S N, Eriksson M A, Vandersypen L M K 2018 Nature 555 633Google Scholar

    [41]

    Chew Y, Tomita T, Mahesh T P, Sugawa S, Léséleuc S D, Ohmori K 2022 Nat. Photonics. 16 724Google Scholar

    [42]

    杨靖北, 丛爽, 陈鼎 2017 控制理论与应用 34 15144Google Scholar

    Yang J B, Cong S, Chen D 2017 J. Control Theory Appl. 34 15144Google Scholar

    [43]

    Gokhale P, Angiuli O, Ding Y, Gui K, Tomesh T, Suchara M, Martonosi M, Chong F T 2020 IEEE Trans. Quantum Eng. 1 1Google Scholar

    [44]

    Huang H Y, Kueng R, Preskill J 2021 Phys. Rev. Lett. 126 190505Google Scholar

  • [1] 杨莹, 曹怀信. 量子混合态的两种神经网络表示. 物理学报, 2023, 72(11): 110301. doi: 10.7498/aps.72.20221905
    [2] 王伟杰, 姜美美, 王淑梅, 曲英杰, 马鸿洋, 邱田会. 基于量子长短期记忆网络的量子图像混沌加密方案. 物理学报, 2023, 72(12): 120301. doi: 10.7498/aps.72.20230242
    [3] 王晨阳, 段倩倩, 周凯, 姚静, 苏敏, 傅意超, 纪俊羊, 洪鑫, 刘雪芹, 汪志勇. 基于遗传算法优化卷积长短记忆混合神经网络模型的光伏发电功率预测. 物理学报, 2020, 69(10): 100701. doi: 10.7498/aps.69.20191935
    [4] 李志军, 曾以成, 李志斌. 改进型细胞神经网络实现的忆阻器混沌电路. 物理学报, 2014, 63(1): 010502. doi: 10.7498/aps.63.010502
    [5] 张旭东, 朱萍, 谢小平, 何国光. 混沌神经网络的动态阈值控制. 物理学报, 2013, 62(21): 210506. doi: 10.7498/aps.62.210506
    [6] 李盼池, 王海英, 戴庆, 肖红. 量子过程神经网络模型算法及应用. 物理学报, 2012, 61(16): 160303. doi: 10.7498/aps.61.160303
    [7] 杨晓阔, 蔡理, 赵晓辉, 冯朝文. 参数不确定量子细胞神经网络与Lorenz超混沌系统的函数投影同步研究. 物理学报, 2010, 59(6): 3740-3746. doi: 10.7498/aps.59.3740
    [8] 楼旭阳, 崔宝同. 混沌时滞神经网络系统的反同步. 物理学报, 2008, 57(4): 2060-2067. doi: 10.7498/aps.57.2060
    [9] 郑鸿宇, 罗晓曙, 吴 雷. 变权小世界生物神经网络的兴奋及优化特性. 物理学报, 2008, 57(6): 3380-3384. doi: 10.7498/aps.57.3380
    [10] 王永生, 孙 瑾, 王昌金, 范洪达. 变参数混沌时间序列的神经网络预测研究. 物理学报, 2008, 57(10): 6120-6131. doi: 10.7498/aps.57.6120
    [11] 行鸿彦, 徐 伟. 混沌背景中微弱信号检测的神经网络方法. 物理学报, 2007, 56(7): 3771-3776. doi: 10.7498/aps.56.3771
    [12] 丁 刚, 钟诗胜. 基于时变阈值过程神经网络的太阳黑子数预测. 物理学报, 2007, 56(2): 1224-1230. doi: 10.7498/aps.56.1224
    [13] 王占山, 张化光, 王智良. 一类混沌神经网络的全局同步. 物理学报, 2006, 55(6): 2687-2693. doi: 10.7498/aps.55.2687
    [14] 何国光, 朱 萍, 陈宏平, 曹志彤. 混沌神经网络的延时反馈控制研究. 物理学报, 2006, 55(3): 1040-1048. doi: 10.7498/aps.55.1040
    [15] 刘光杰, 单 梁, 戴跃伟, 孙金生, 王执铨. 基于混沌神经网络的单向Hash函数. 物理学报, 2006, 55(11): 5688-5693. doi: 10.7498/aps.55.5688
    [16] 王占山, 张化光. 时滞递归神经网络中神经抑制的作用. 物理学报, 2006, 55(11): 5674-5680. doi: 10.7498/aps.55.5674
    [17] 张 强, 高 琳, 王 超, 许 进. 时滞双向联想记忆神经网络的全局稳定性. 物理学报, 2003, 52(7): 1600-1605. doi: 10.7498/aps.52.1600
    [18] 蔡 理, 马西奎, 王 森. 量子细胞神经网络的超混沌特性研究. 物理学报, 2003, 52(12): 3002-3006. doi: 10.7498/aps.52.3002
    [19] 何国光, 曹志彤. 混沌神经网络的控制. 物理学报, 2001, 50(11): 2103-2107. doi: 10.7498/aps.50.2103
    [20] 马余强, 张玥明, 龚昌德. Hopfield神经网络模型的恢复特性. 物理学报, 1993, 42(8): 1356-1360. doi: 10.7498/aps.42.1356
计量
  • 文章访问数:  4353
  • PDF下载量:  102
  • 被引次数: 0
出版历程
  • 收稿日期:  2022-10-08
  • 修回日期:  2023-01-11
  • 上网日期:  2023-02-01
  • 刊出日期:  2023-03-05

/

返回文章
返回