期刊文献+

基于快速持续对比散度的卷积受限玻尔兹曼机 被引量:7

Convolutional Restricted Boltzmann Machine Based on Fast Persistent Contrastive Divergence
下载PDF
导出
摘要 受限玻尔兹曼机是深度学习中的重要模型,以其为基础的卷积受限玻尔兹曼机模型被广泛应用于图像处理与语音识别等领域,但其存在训练时间过长的问题。为此,使用快速持续对比散度(FPCD)算法对卷积受限玻尔兹曼机进行学习,从而提高模型的学习速度和分类精度。实验结果表明,与PCD,CD_1等算法相比,FPCD算法可有效提高卷积受限玻尔兹曼机的分类性能。 Restricted Boltzmann Machine(RBM) is one of the important models in deep learning. The Convolutional RBM(CRBM) model based on RBM is widely used in image processing and speech recognition. However, the long training time is still a problem of the CRBM model that cannot be ignored. In this paper, the Fast Persistent Contrastive Divergence (FPCD) algorithm is used to train the CRBM, to improve the learning speed and classification accuracy of the model. Experimental results show that, compared with PCD, CD 1 and other algorithms, FPCD can improve the classification performance of CRBM.
出处 《计算机工程》 CAS CSCD 北大核心 2016年第9期174-179,共6页 Computer Engineering
基金 国家自然科学基金资助项目(61163036 61163039) 甘肃省科技计划基金资助项目(1606RJZA047) 甘肃省高校基本科研业务费专项基金资助项目 甘肃省高校研究生导师基金资助项目(1201-16) 西北师范大学第三期知识与创新工程科研骨干基金资助项目(nwnu-kjcxgc-03-67)
关键词 卷积受限玻尔兹曼机 深度学习 快速持续对比散度 训练时间 分类精度 Convolutional Restricted Boltzmann Machine (CRBM) deep learning Fast Persistent Contrastive Divergence (FPCD) train time classification accuracy
  • 相关文献

参考文献23

  • 1余凯,贾磊,陈雨强,徐伟.深度学习的昨天、今天和明天[J].计算机研究与发展,2013,50(9):1799-1804. 被引量:610
  • 2Hinton G. A Practical Guide to Training Restricted Boltzma-nn Machines [ J ]. Momentum,2010,9 ( 1 ) :926-946.
  • 3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. 被引量:71
  • 4Hinton G E. Training Poducts of Eperts by Mnimizing Cntrastive Dvergence ~ J ]. Neural Computation, 2002, 14(8) -1771-1800.
  • 5Hinton G E, Salakhutdinov R R. Replicated Softmax:An Undirected Topic Model I C ]//Proceedings of NIPS' 09. S. 1. I .Morgan Kaufmann ,2009 . 1607-1614.
  • 6Salakhutdinov R, Mnih A, Hinton G. Restricted Boltzma- nn Machines for Collaborative FilteringI C]//Proceedings of the 24th International Conference on Machine Learning. New York, USA: ACM Press,2007 : 791-798.
  • 7Taylor G W,Hinton G E, Roweis S T. Modeling Human Motion Using Binary Latent Variables~ C 1//Proceedings of NIPS' 06. ~ S. 1. ] :Morgan Kaufmann ,2006 : 1345-1352.
  • 8Lee H,Grosse R, Ranganath R, et al. Convolutional Deep Belief Networks for Scalable Unsupervised Learning of Hierarchical Representations l C l//Proceedings of the 26th Annual International Conference on Machine Learning. New York ,USA : ACM Press ,2009:609-616.
  • 9Zeiler M D, Fergus R. Stochastic Pooling for Regularizetion of Deep Convolutional Neural Networks [ C ]//Proceedings of International Conference on Representaiton Learning. Washington D. C.,USA :IEEE Press ,2013.
  • 10Gao Jingyu,Yang Jinfu, Wang Guanghui, et al. A Novel Feature Extraction Method for Scene Recognition Based on Centered Convolutional Restricted Boltzmann Machines ~ J ~. Computer Science ,2015,11 ( 2 ) : 14-19.

二级参考文献60

  • 1MarkoffJ. How many computers to identify a cat?[NJ The New York Times, 2012-06-25.
  • 2MarkoffJ. Scientists see promise in deep-learning programs[NJ. The New York Times, 2012-11-23.
  • 3李彦宏.2012百度年会主题报告:相信技术的力量[R].北京:百度,2013.
  • 410 Breakthrough Technologies 2013[N]. MIT Technology Review, 2013-04-23.
  • 5Rumelhart D, Hinton G, Williams R. Learning representations by back-propagating errors[J]. Nature. 1986, 323(6088): 533-536.
  • 6Hinton G, Salakhutdinov R. Reducing the dimensionality of data with neural networks[J]. Science. 2006, 313(504). Doi: 10. 1l26/science. 1127647.
  • 7Dahl G. Yu Dong, Deng u, et a1. Context-dependent pre?trained deep neural networks for large vocabulary speech recognition[J]. IEEE Trans on Audio, Speech, and Language Processing. 2012, 20 (1): 30-42.
  • 8Jaitly N. Nguyen P, Nguyen A, et a1. Application of pretrained deep neural networks to large vocabulary speech recognition[CJ //Proc of Interspeech , Grenoble, France: International Speech Communication Association, 2012.
  • 9LeCun y, Boser B, DenkerJ S. et a1. Backpropagation applied to handwritten zip code recognition[J]. Neural Computation, 1989, I: 541-551.
  • 10Large Scale Visual Recognition Challenge 2012 (ILSVRC2012)[OLJ.[2013-08-01J. http://www. image?net.org/challenges/LSVRC/2012/.

共引文献664

同被引文献32

引证文献7

二级引证文献22

相关作者

内容加载中请稍等...

相关机构

内容加载中请稍等...

相关主题

内容加载中请稍等...

浏览历史

内容加载中请稍等...
;
使用帮助 返回顶部