Please wait a minute...
浙江大学学报(工学版)
JOURNAL OF ZHEJIANG UNIVERSITY (ENGINEERING SCIENCE)
    
New hybrid sparse penalty mechanism of restricted Boltzmann machine
LIU Kai1, ZHANG Li-min1, ZHANG Chao2
1. Department of Electronic and Information Engineering, Naval Aeronautical and Astronautical University, Yantai 264001, China; 2. Ordnance Branch, Equipment Department of South China Sea Fleet, Zhanjiang 524001, China
Download:   PDF(1691KB) HTML
Export: BibTeX | EndNote (RIS)      

Abstract  

A new hybrid sparse penalty mechanism (HSPM) was proposed to resolve the features homogenization problem of restricted Boltzmann machine (RBM). HSPM was based on the existing sparse restricted Boltzmann machine (SRBM). Since the statistical correlation among hidden units, a cross-entropy factor to optimize the training of RBMs was first implemented by HSPM. Then, hidden units were grouped according to adaptive grouping strategy based on the column similarity of connection weights. Finally, hidden units sparse processing was carried out in the form of sparse group restricted Boltzmann machine (SGRBM). The experimental results confirmed that HSPM could effectively resolve the feature homogenization problem of RBM and was better than ever sparse penalty factor on degree of signals sparsity. HSPM can improve the feature extraction capability of RBM and be applied to the training of deep Boltzmann machine (DBM) successfully.

Published: 01 June 2015
CLC:  TP 391  
Service
E-mail this article
Add to my bookshelf
Add to citation manager
E-mail Alert
RSS
Articles by authors
Cite this article:

LIU Kai1, ZHANG Li-min1, ZHANG Chao2. New hybrid sparse penalty mechanism of restricted Boltzmann machine. JOURNAL OF ZHEJIANG UNIVERSITY (ENGINEERING SCIENCE), 2015, 49(6): 1070-1078.

URL:

http://www.zjujournals.com/eng/10.3785/j.issn.1008-973X.2015.06.010     OR     http://www.zjujournals.com/eng/Y2015/V49/I6/1070


受限玻尔兹曼机的新混合稀疏惩罚机制

为解决受限玻尔兹曼机（RBM）在学习过程中出现的特征同质化问题,在RBM已有的稀疏模型基础上提出新的混合稀疏惩罚机制（HSPM）.鉴于隐单元之间存在的统计相关性,该机制通过在RBM训练过程中引入交叉熵稀疏惩罚因子,实现对RBM的初步处理；按照基于RBM连接权值列相似性的自适应分组策略，构建稀疏组RBM,并按照稀疏组受限玻尔兹曼机（SGRBM）的形式继续进行隐单元稀疏化.实验结果表明：HSPM能够有效解决RBM特征同质化问题,在隐单元的稀疏程度上优于以往的稀疏惩罚因子,可以整体提高RBM的特征提取能力,并可以成功应用于深度玻尔兹曼机（DBM）的训练.

［1］ 刘建伟,刘媛,罗雄麟.玻尔兹曼机研究进展［J］.计算机研究与发展,2014, 51(1): 1-16.
LIU Jian-wei, LIU Yuan, LUO Xiong-lin. Research and development on boltzmann machine ［J］. Journal of Computer Research and Development, 2014, 51(1): 1-16.
［2］ 陈宇,郑德权,赵铁军.基于Deep Belief Nets的中文名实体关系抽取 ［J］.软件学报, 2012, 23(10): 2572-2585.
CHEN Yu, ZHENG De-quan, ZHAO Tie-jun. Chinese relation extraction based on deep belief nets ［J］. Journal of Software, 2012, 23(10): 2572-2585.
［3］ MOHAMED A, DAHL G E, HINTON G E. Acoustic modeling using deep belief networks ［J］. IEEE Transactions on Audio, Speech, and Language Processing, 2012, 20(1): 14-22.
［4］ SCHMAH T, HINTON G E, ZEMEL R, et al. Generative versus discriminative training of RBMs for classification of fMRI images ［C］∥ Proceedings of the 22rd Annual Conference on Neural Information Processing Systems. Whistler: NIPS, 2008: 1409-1416.
［5］ MEMISEVIC R, HINTON G E. Unsupervised learning of image transformations ［C］∥ Proceedings of 2007 IEEE Conference on Computer Vision and Pattern Recognition. Piscataway: IEEE, 2007: 18.
［6］ TAYLOR G W, SIGAL L, FLEET D J, et al. Dynamical binary latent variable models for 3D human pose tracking ［C］∥ Proceedings of 2010 IEEE Conference on Computer Vision and Pattern Recognition. Piscataway: IEEE, 2010: 631-638.
［7］ 林妙真.基于深度学习的人脸识别研究［D］.大连:大连理工大学,2013: 24-69.
LIN Miao-zhen. Research on face recognition based on deep learning ［D］. Dalian: Dalian University of Technology, 2013: 24-69.
［8］ 罗恒.基于协同过滤视角的受限玻尔兹曼机研究［D］.上海,上海交通大学,2011: 70-79.
LUO Heng. Restricted Boltzmann machines: a collaborative filtering perspective ［D］. Shanghai: Shanghai Jiao Tong University, 2011: 70-79.
［9］ LEE H, EKANADHAM C, NG A. Sparse deep belief net model for visual area V2 ［C］∥ Proceedings of the 21rd Annual Conference on Neural Information Processing Systems. Vancouver: NIPS, 2007: 873-880.
［10］ HINTON G E. A practical guide to training restricted Boltzmann machines ［R］. Canada, Toronto University: Machine Learning Group, 2010.
［11］ LUO H, CHANG Y N, RUI M S, et al. Sparse group restricted boltzmann machines ［C］∥ Proceedings of 25th Conference on Innovative Applications of Artificial Intelligence. San Francisco : AAAI, 2011: 1207-1216.
［12］ GUO R, QI H. Partially-sparse restricted boltzmann machine for background modeling and subtraction ［C］∥ Proceedings of 2013 IEEE Conference on Machine Learning and Applications. Piscataway: IEEE, 2013: 209-214.
［13］ 吴一全,张晓杰,吴诗婳.2维对称交叉熵图像阈值分割［J］.中国图像图形学报,2011,11(8): 122-126.
WU Yi-quan, ZHANGE Xiao-jie, WU Shi-hua. Two-dimensional symmetric cross-entropy image thresholding ［J］. Journal of Image and Graphics, 2011, 11(8): 122-126.
［14］ BENGIO Y. Learning deep architectures for AI ［J］. Foundations and Trends in Machine Learning, 2009, 2(1): 11-27.
［15］ LENG B, ZHANG X, YAO M, et al. A 3D model recognition mechanism based on deep Boltzmann machines ［J］. Neuro Computing, 2015, 151(2): 593-602.
［16］ SUSSKIND J. The Toronto face database ［R］. Canada, Toronto University: Machine Learning Group, 2011.
［17］ CHANG C C, LIN C J. LIBSVM: a library for support vector machines ［J］. ACM Transactions on Intelligent Systems and Technology, 2011, 2(3): 27-33.
［18］ KUREMOTO T, KIMURA S, KOBAYASHI K, et al. Time series forecasting using a deep belief network with restricted Boltzmann machines ［J］. Neuro computing, 2014, 137(5): 47-56.
［19］ SRIVASTAVA N, SALAKHUTDINOV R. Multimodal learning with deep Boltzmann machines ［J］. Journal of Machine Learning Research, 2014, 15(4): 2949-2980.
［20］ SALAKHUTDINOV R, HINTON G E. Deep Boltzmann machines ［C］∥ Proceedings of 12th International Conference on Artificial Intelligence and Statistics. Florida: AISTATS, 2009: 448-455.
[1] HE Xue-jun, WANG Jin, LU Guo-dong, LIU Zhen-yu, CHEN Li, JIN Jing. 3D head portrait sculpture by industrial robot based on triangular mesh slicing and collision detection[J]. JOURNAL OF ZHEJIANG UNIVERSITY (ENGINEERING SCIENCE), 2017, 51(6): 1104-1110.
[2] WANG Hua, HAN Tong-yang, ZHOU Ke. KeyGraph-based community detection algorithm for public security intelligence[J]. JOURNAL OF ZHEJIANG UNIVERSITY (ENGINEERING SCIENCE), 2017, 51(6): 1173-1180.
[3] YOU Hai-hui, MA Zeng-yi, TANG Yi-jun, WANG Yue-lan, ZHENG Lin, YU Zhong, JI Cheng-jun. Soft measurement of heating value of burning municipal solid waste for circulating fluidized bed[J]. JOURNAL OF ZHEJIANG UNIVERSITY (ENGINEERING SCIENCE), 2017, 51(6): 1163-1172.
[4] BI Xiao-jun, WANG Jia-hui. Teaching-learning-based optimization algorithm with hybrid learning strategy[J]. JOURNAL OF ZHEJIANG UNIVERSITY (ENGINEERING SCIENCE), 2017, 51(5): 1024-1031.
[5] JIANG Xin-long, CHEN Yi-qiang, LIU Jun-fa, HU Li-sha, SHEN Jian-fei. Wearable system to support proximity awareness for people with autism[J]. JOURNAL OF ZHEJIANG UNIVERSITY (ENGINEERING SCIENCE), 2017, 51(4): 637-647.
[6] WANG Liang, YU Zhi-wen, GUO Bin. Moving trajectory prediction model based on double layer multi-granularity knowledge discovery[J]. JOURNAL OF ZHEJIANG UNIVERSITY (ENGINEERING SCIENCE), 2017, 51(4): 669-674.
[7] LIAO Miao, ZHAO Yu-qian, ZENG Ye-zhan, HUANG Zhong-chao, ZHANG Bing-kui, ZOU Bei-ji. Automatic segmentation for cell images based on support vector machine and ellipse fitting[J]. JOURNAL OF ZHEJIANG UNIVERSITY (ENGINEERING SCIENCE), 2017, 51(4): 722-728.
[8] MU Jing-jing, ZHAO Xin-yue, HE Zai-xing, ZHANG Shu-you. Contour reconstruction of overlapped bubbles based on concave-convex transformation and circle fitting[J]. JOURNAL OF ZHEJIANG UNIVERSITY (ENGINEERING SCIENCE), 2017, 51(4): 714-721.
[9] HUANG Zheng-yu, JIANG Xin-long, LIU Jun-fa, CHEN Yi-qiang, GU Yang. Fusion feature based semi-supervised manifold localization method[J]. JOURNAL OF ZHEJIANG UNIVERSITY (ENGINEERING SCIENCE), 2017, 51(4): 655-662.
[10] LIU Lei, YANG Peng, LIU Zuo-jun. Locomotion-Mode recognition using multiple kernel relevance vector machine[J]. JOURNAL OF ZHEJIANG UNIVERSITY (ENGINEERING SCIENCE), 2017, 51(3): 562-571.
[11] GUO Meng-li, DA Fei-peng, DENG Xing, GAI Shao-yan. 3D face recognition based on keypoints and local feature[J]. JOURNAL OF ZHEJIANG UNIVERSITY (ENGINEERING SCIENCE), 2017, 51(3): 584-589.
[12] DAI Cai-yan, CHEN Ling, LI Bin, CHEN Bo-lun. Sampling-based link prediction in complex networks[J]. JOURNAL OF ZHEJIANG UNIVERSITY (ENGINEERING SCIENCE), 2017, 51(3): 554-561.
[13] WANG Hai jun, GE Hong juan, ZHANG Sheng yan. Fast object tracking algorithm via kernel collaborative presentation[J]. JOURNAL OF ZHEJIANG UNIVERSITY (ENGINEERING SCIENCE), 2017, 51(2): 399-407.
[14] ZHANG Ya nan, CHEN De yun, WANG Ying jie, LIU Yu peng. Incremental graph pattern matching based dynamic recommendation method for cold-start user[J]. JOURNAL OF ZHEJIANG UNIVERSITY (ENGINEERING SCIENCE), 2017, 51(2): 408-415.
[15] LIU Yu peng, QIAO Xiu ming, ZHAO Shi lei, MA Chun guang. Deep combination of large-scale features in statistical machine translation[J]. JOURNAL OF ZHEJIANG UNIVERSITY (ENGINEERING SCIENCE), 2017, 51(1): 46-56.