期刊文献+

深度学习结构和算法比较分析 被引量:33

Note on deep architecture and deep learning algorithms
下载PDF
导出
摘要 Hinton等人提出的深度机器学习,掀起了神经网络研究的又一个浪潮.介绍了深度机器学习的基本概念和基本思想.对于目前比较成熟的深度机器学习结构深度置信网DBNs和约束Boltzmann机(RBM)的结构和无监督贪婪学习算法作了比较详细的介绍和比较,并对算法的改进方向提出了有建设性的意见,对深度机器学习的未来发展方向和目前存在的问题进行了深刻的分析。 Deep architectures proposed by Hinton et al stir up another study wave in neural networks.This paper introduced the idea and basic concepts in deep learning.DBNs and RBMs are the advanced structures of deep learning,whose structures and effective learning algorithm are also introduced in detail in this paper.In addition,open questions in deep learning are also briefly displayed so that researchers who are interested in can devote themselves into those questions and solve them.
出处 《河北大学学报(自然科学版)》 CAS 北大核心 2012年第5期538-544,共7页 Journal of Hebei University(Natural Science Edition)
基金 保定市科学技术研究与发展指导计划项目(12ZG005) 河北省高等学校科学研究计划项目(JYGH2011011)
关键词 深度机器学习 无监督贪婪学习算法 DBNs RBMs deep learning greedy learning algorithm DBNs RBMs
  • 相关文献

参考文献12

  • 1HAYKIN S. Neural Networks: A comprehensive foundation[M]. 2nd ed. New York: Prentice-Hall, 1999.
  • 2BENGIO Y. Learning deep architectures for AI[J]. Foundations and Trends in Machine Learning, 2009, 2(1):1 -127.
  • 3HINTON G E, MCCLELLAND J L, RUMELHART D E. Distributed Representations[M]. Cambridge: MIT Press, 1986.
  • 4HINTON G E, OSINDERO S. A fast learning algorithm for deep belief nets[J]. Neural Computation, 2006, 18:1527 - 1554.
  • 5HUBEL D, WIESEL T. Receptive fields, binocular interaction, and functional architecture in the cat's visual cortex[J]. Journal of Physiology, 1962, 160 : 106 - 154.
  • 6LECUNY, KAVUKCUOGLUK, FARABET C. Convolutional networks and applications in vision[Z]. International Symposium on Circuits and Systems, Paris, 2010.
  • 7LASERSON J. From neural networks to deep learning: zeroing in on the human brain [J]. XRDS, 2011, 18(1) :29 -34.
  • 8LECUNY, BOTTOU L, BENGIO Y, et al. Gradient-based learning applied to document recognition[J]. Proceedings of IEEE, 1998, 86(11): 2278-2324.
  • 9ERHAND, BENGIO Y, COURVILE A, et al. Why does unsupervised pre-training help deep learning[J]. Journal of Machine Learning Research, 2010, 11:625 - 660.
  • 10BENGIO Y, LAMBLIN P, POPOVICI D, et al. Greedy layer-wise training of deep networks[J]. Advances in Neural Information Processing Systems, 2007, 19:153 - 160.

同被引文献282

引证文献33

二级引证文献417

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