2.845

2023影响因子

(CJCR)

  • 中文核心
  • EI
  • 中国科技核心
  • Scopus
  • CSCD
  • 英国科学文摘

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

一种基于胶质细胞链的改进深度信念网络模型

耿志强 张怡康

耿志强, 张怡康. 一种基于胶质细胞链的改进深度信念网络模型. 自动化学报, 2016, 42(6): 943-952. doi: 10.16383/j.aas.2016.c150727
引用本文: 耿志强, 张怡康. 一种基于胶质细胞链的改进深度信念网络模型. 自动化学报, 2016, 42(6): 943-952. doi: 10.16383/j.aas.2016.c150727
GENG Zhi-Qiang, ZHANG Yi-Kang. An Improved Deep Belief Network Inspired by Glia Chains. ACTA AUTOMATICA SINICA, 2016, 42(6): 943-952. doi: 10.16383/j.aas.2016.c150727
Citation: GENG Zhi-Qiang, ZHANG Yi-Kang. An Improved Deep Belief Network Inspired by Glia Chains. ACTA AUTOMATICA SINICA, 2016, 42(6): 943-952. doi: 10.16383/j.aas.2016.c150727

一种基于胶质细胞链的改进深度信念网络模型

doi: 10.16383/j.aas.2016.c150727
基金项目: 

北京市自然科学基金 4162045

国家自然科学基金 61374166

教育部博士点基金 20120010110010

详细信息
    作者简介:

    张怡康 北京化工大学信息科学与技术学院硕士研究生. 主要研究方向为神经网络, 深度学习. E-mail: zykh11@163.com

    通讯作者:

    耿志强 北京化工大学信息科学与技术学院教授. 主要研究方向为神经网络, 数据挖掘, 过程建模与系统优化. 本文通信作者. E-mail: gengzhiqiang@mail.buct.edu.cn

An Improved Deep Belief Network Inspired by Glia Chains

Funds: 

Natural Science Founda-tion of Beijing 4162045

Supported by National Natural Science Foundation of China 61374166

Ph. D. Programs Foundation of Ministry of Educa-tion of China 20120010110010

More Information
    Author Bio:

    ZHANG Yi-Kang Master student at the College of Information Scienceand Technology, Beijing University of Chemical Technology. His research in- terest covers neural networks and deep learning

    Corresponding author: GENG Zhi-Qiang Professor at the College of Information Science and Technology, Beijing University of Chemical Technology. His research interest covers neural networks, data mining, process modeling and system opti- mization. Corresponding author of this paper
  • 摘要: 深度信念网络(Deep belief network, DBN) 是一种从无标签数据学习特征的多层结构模型. 在同一层单元间缺少连接, 导致数据中的深度关联特征难以提取. 受到人脑中胶质神经细胞机制的启示, 提出一种基于胶质细胞链的改进 DBN 模型及其学习算法, 以提取更多数据信息. 在标准图像分类数据集上的实验结果表明, 与其他几种模型相比, 本文提出的改进 DBN 模型可以提取更为优秀的图像特征, 提高分类准确率.
  • 图  1  RBM 结构示意图

    Fig.  1  The structure of RBM

    图  2  多步采样的CD 算法过程

    Fig.  2  Multistep sampling in CD algorithm

    图  3  胶质细胞链改进的RBM 及其组成的DBN 模型

    Fig.  3  Improved RBMs based on glia chains and a DBN composed of these RBMs

    图  4  改进DBN 的训练过程

    Fig.  4  Training process of the improved DBN

    图  5  RBM (上) 和胶质细胞链改进的RBM (下) 学习特征的可视化

    Fig.  5  Visualization of features learned by RBM (above) and improved RBM (below)

    图  6  RBM 及胶质细胞改进RBM 在CIFAR-10 数据集上的测试分类错误率

    Fig.  6  Test error rate of RBM and RBM with glia chain on CIFAR-10 dataset

    图  7  Rectangles images 数据集上RBM 及胶质细胞改进 RBM 的测试分类错误率

    Fig.  7  Test error rate of RBM and RBM with glia chain on Rectangles images dataset

    图  8  胶质效果权重参数不同取值下改进DBN 模型的测试分类错误率

    Fig.  8  Testing error rate of improved DBN with diαerent values of glia eαect weight

    图  9  胶质衰减因子参数不同取值下改进DBN 模型的测试分类错误率

    Fig.  9  Testing error rate of improved DBN with diαerent values of attenuation factor

    图  10  胶质阈值参数不同取值下改进DBN 模型的测试分类错误率

    Fig.  10  Testing error rate of improved DBN with diαerent values of glia threshold

    表  1  MNIST 数据集上不同模型的测试结果

    Table  1  Testing results of diαerent models on MNIST dataset

    模型 200 隐含单元 300 隐含单元 500 隐含单元
    测试 收敛 测试 收敛 测试 收敛
    错误率 时间 错误率 时间 错误率 时间
    (%) (s) (%) (s) (%) (s)
    RBM 3.03 70.06 2.83 94.48 2.55 146.23
    Sparse auto-encoder 3.34 121.01 2.91 153.67 2.59 198.21
    BP neural network 4.57 142.42 4.35 187.17 4.1 215.88
    RBM + Glial chain 2.82 65.27 2.62 90.42 2.4 137.91
    下载: 导出CSV

    表  2  MNIST 数据集上传统DBN 及改进DBN 的训练及测试错误率及收敛时间

    Table  2  Training, testing error rate and convergence time of DBN and improved DBN on MNIST dataset

    模型 训练错误率(%) 测试错误率(%) 收敛时间(s)
    DBN 1.69 2.59 184.07
    改进DBN 1.05 1.53 176.72
    下载: 导出CSV

    表  3  MNIST 数据集上传统DBN 及改进DBN 的FP 及FN 数据

    Table  3  FP and FN data of DBN and improved DBN on MNIST dataset

    模型 类别1 类别2 类别3
    FP FN FP FN FP FN
    DBN 145 10 137 13 133 24
    改进DBN 28 9 12 10 33 16
    下载: 导出CSV

    表  4  MNIST 数据集上改进DBN 取得的最优结果与其他模型已有结果的比较

    Table  4  Comparison of DBN and other models0 bestresults on MNIST dataset

    模型 测试错误率(%)
    1 000 RBF + Linear classifer 3.60[20]
    DBN,using SparseRBMs pre-training a 784-500-500-2 000 network1.87[26]
    Boosted trees (17 leaves) 1.53[27]
    3-layer NN,500 + 300 HU,softmax,cross-entropy,weight decay1.51[28]
    SVM,Gaussian kernel 1.40[29]
    DBN,using RBMs pre-training a 784-500-500-2 000 network1.20[2]
    DBN,using RBMs with glial chain pre-training a 784-500-500-2 000 network 1.09
    下载: 导出CSV

    表  5  CIFAR-10 数据集上DBN 及胶质细胞改进DBN 的训练和测试分类错误率及收敛时间

    Table  5  Training, testing error rate and convergence time of DBN and improved DBN on CIFAR-10 dataset

    模型 训练错误率(%) 测试错误率(%) 收敛时间(s)
    DBN 32.67 50.07 474.21
    改进DBN 30.4 46.19 463.19
    下载: 导出CSV

    表  6  CIFAR-10 数据集上DBN 及胶质细胞改进DBN 的FP 和FN 数据

    Table  6  FP and FN data of DBN and improved DBN on CIFAR-10 dataset

    类别 Airplane Automobile Bird
    FP FN FP FN FP FN
    DBN 8 781 421 8 017 800 7 817 1 000
    改进DBN 4 986 36 5 074 333 4 731 676
    下载: 导出CSV

    表  7  Rectangles images 数据集上DBN 及胶质细胞改进DBN 的训练和测试错误率、收敛时间、FP 和FN 数据

    Table  7  Training, testing error rate, convergence time, and FP, FN data of DBN and improved DBN on Rectangles images dataset

    模型 训练错误率(%) 测试错误率(%) 收敛时间(s) FP FN
    DBN 1.61 3.22 90.03 7 9
    改进DBN 0.59 1.4 46.3 5 2
    下载: 导出CSV
  • [1] Kruger N, Janssen P, Kalkan S, Lappe M, Leonardis A, Piater J, Rodriguez-Sanchez A J, Wiskott L. Deep hierarchies in the primate visual cortex: what can we learn for computer vision. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2013, 35(8): 1847-1871
    [2] Hinton G E, Salakhutdinov R R. Reducing the dimensionality of data with neural networks. Science, 2006, 313(5786): 504-507
    [3] Hinton G E, Osindero S, Teh Y W. A fast learning algorithm for deep belief nets. Neural Computation, 2006, 18(7): 1527-1554
    [4] Bengio Y, Lamblin P, Popovici D, Larochelle H. Greedy layer-wise training of deep networks. In: Proceedings of Advances in Neural Information Processing Systems 19. Cambridge: MIT Press, 2007. 153-160
    [5] Lee H, Grosse R, Ranganath R, Ng A Y. Unsupervised learning of hierarchical representations with convolutional deep belief networks. Communications of the ACM, 2011, 54(10): 95-103
    [6] Huang G B, Lee H, Learned-Miller E. Learning hierarchical representations for face verification with convolutional deep belief networks. In: Proceedings of the 2012 IEEE Conference on Computer Vision&Pattern Recognition. Providence, RI: IEEE, 2012. 2518-2525
    [7] Liu P, Han S Z, Meng Z B, Tong Y. Facial expression recognition via a boosted deep belief network. In: Proceedings of the 2014 IEEE Conference on Computer Vision&Pattern Recognition. Columbus, OH: IEEE, 2014. 1805-1812
    [8] Roy P P, Chherawala Y, Cheriet M. Deep-belief-network based rescoring approach for handwritten word recognition. In: Proceedings of the 14th International Conference on Frontiers in Handwriting Recognition. Heraklion: IEEE, 2014. 506-511
    [9] Mohamed A R, Dahl G E, Hinton G. Acoustic modeling using deep belief networks. IEEE Transactions on Audio, Speech,&Language Processing, 2012, 20(1): 14-22
    [10] Kang S Y, Qian X J, Meng H L. Multi-distribution deep belief network for speech synthesis. In: Proceedings of the 2013 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). Vancouver, BC: IEEE, 2013. 8012-8016
    [11] Haydon P G. GLIA: listening and talking to the synapse. Nature Reviews Neuroscience, 2001, 2(3): 185-193
    [12] Ikuta C, Uwate Y, Nishio Y. Investigation of multi-layer perceptron with pulse glial chain. IEICE Technical Report Nonlinear Problems, 2011, 111(62): 45-48 (in Japanese)
    [13] Fischer A, Igel C. An introduction to restricted Boltzmann machines. In: Proceedings of the 17th Iberoamerican Congress on Progress in Pattern Recognition, Image Analysis, Computer Vision, and Applications. Lecture Notes in Computer Science. Buenos Aires, Argentina: Springer, 2012. 14-36
    [14] Deng L, Yu D. Deep learning: methods and applications. Foundations&Trends® in Signal Processing, 2013, 7(3-4): 197-387
    [15] Hinton G E. Training products of experts by minimizing contrastive divergence. Neural Computation, 2002, 14(8): 1771-1800
    [16] Bengio Y. Learning deep architectures for AI. Foundations&Trends® in Machine Learning, 2009, 2(1): 1-127
    [17] Ikuta C, Uwate Y, Nishio Y. Multi-layer perceptron with positive and negative pulse glial chain for solving two-spirals problem. In: Proceedings of the 2012 International Joint Conference on Neural Networks. Brisbane, QLD: IEEE, 2012. 1-6
    [18] Hinton G, Deng L, Yu D, Dahl G E, Mohamed A R, Jaitly N, Senior A, Vanhoucke V, Nguyen P, Sainath T N, Kingsbury B. Deep neural networks for acoustic modeling in speech recognition: the shared views of four research groups. IEEE Signal Processing Magazine, 2012, 29(6): 82-97
    [19] Hinton G E. A practical guide to training restricted Boltzmann machines. Neural Networks: Tricks of the Trade (2nd edition). Berlin Heidelberg: Springer, 2012. 599-619
    [20] Lecun Y, Bottou L, Bengio Y, Haffner P. Gradient-based learning applied to document recognition. Proceedings of the IEEE, 1998, 86(11): 2278-2324
    [21] Krizhevsky A, Hinton G. Learning Multiple Layers of Features from Tiny Images, Technical Report, University of Toronto, Canada, 2009.
    [22] Larochelle H, Erhan D, Courville A, Bergstra J, Bengio Y, Ghahramani Z. An empirical evaluation of deep architectures on problems with many factors of variation. In: Proceedings of the 24th International Conference on Machine Learning. Oregon, USA: ICML, 2007. 473-480
    [23] Luo Y X, Wan Y. A novel efficient method for training sparse auto-encoders. In: Proceedings of the 6th International Congress on Image&Signal Processing. Hangzhou, China: IEEE, 2013. 1019-1023
    [24] Rumelhart D E, Hinton G E, Williams R J. Learning internal representations by error propagation. Neurocomputing: Foundations of Research. Cambridge: MIT Press, 1988. 673-695
    [25] Platt J C. Using analytic Qp and sparseness to speed training of support vector machines. In: Proceedings of Advances in Neural Information Processing Systems 11. Cambridge: MIT Press, 1999. 557-563
    [26] Swersky K, Chen B, Marlin B, de Freitas N. A tutorial on stochastic approximation algorithms for training restricted Boltzmann machines and deep belief nets. In: Proceedings of the 2010 Information Theory and Applications Workshop (ITA). San Diego, USA: IEEE, 2010. 1-10
    [27] Kégl B, Busa-Fekete R. Boosting products of base classifiers. In: Proceedings of the 26th International Conference on Machine Learning. Montreal, Canada: ACM, 2009. 497-504
    [28] Hinton G E. What kind of a graphical model is the brain. In: Proceedings of the 19th International Joint Conference on Artificial Intelligence. San Francisco, CA, USA: Morgan Kaufmann Publishers Inc., 2005. 1765-1775
    [29] Cortes C, Vapnik V. Support-vector networks. Machine Learning, 1995, 20(3): 273-297
  • 加载中
图(10) / 表(7)
计量
  • 文章访问数:  1799
  • HTML全文浏览量:  234
  • PDF下载量:  1345
  • 被引次数: 0
出版历程
  • 收稿日期:  2015-10-31
  • 录用日期:  2016-05-03
  • 刊出日期:  2016-06-20

目录

    /

    返回文章
    返回