期刊文献+

机器学习及其算法和发展研究 被引量:130

Research on Machine Learning with Algorithm and Development
下载PDF
导出
摘要 目前,机器学习领域的研究与应用取得了巨大进展,我们有必要对机器学习有个全面的认识。为此,本文对机器学习进行了较为系统的介绍,从机器学习的概念开始,综述了机器学习的发展简史及其分类,然后重点分析了机器学习的经典算法,接下来阐述了机器学习的最新研究进展、愿景及应用,最后探讨了机器学习面临的挑战。 Machine learning(ML) has made great progress now and is playing a more and more important role in AI, it' s needful to know well about ML. For this purpose, this paper attempted to provide novices with a guide, so it introduced ML systematically. Firstly, this article presented the concept, brief history of development and classification of ML. Secondly, we focused on the three classical algorithm of ML, inclu- ding BP, CNN, DP. Thirdly,it introduced the latest research, vision and application of ML. Finally, it con- cluded the challenges of ML.
作者 张润 王永滨
出处 《中国传媒大学学报(自然科学版)》 2016年第2期10-18,24,共10页 Journal of Communication University of China:Science and Technology
关键词 机器学习 视觉皮层 后向传播 卷积神经网络 深度学习 machine learning visual cortex BP CNN deep learning
  • 相关文献

参考文献36

  • 1王琦,操晓春.中国计算机学会通讯[J].2015,P60-62. 被引量:1
  • 2WarrenS McCulloch and Walter Pitts. A logical calculus of the ideas immanentin nervous activity. The bulletin of mathematical biophysics, 1943,5 (4) :115 -133. 被引量:1
  • 3Hopfield J J. Neural Networks and Physical Sys- tems with Emergent Collective Computational Abil- ities, Proc Natl Aead Sci. USA, 1982, (79) : 2254 - 2558. 被引量:1
  • 4E Rumelhart, G E Hinton, R J Williams. Learn- ng internal representations by error propagation. ature , 1986,323 (99) :533 - 536. 被引量:1
  • 5http://deepleaming, stanford, edu/wiki/index. php/UFLDL_Tutorial. 被引量:1
  • 6http://blog, csdn. net/datoubo/article/details/ 8577366. 被引量:1
  • 7Geoffery E Hinton, Salakhutdinov RR. Reducing the dimensionality of data with neural networks. Science, 2006,313 (5786) :504 - 7. 被引量:1
  • 8http://www, ccf. org. cn/sites/ccf/xhdtnry, jsp? contentId = 2873667830199. 被引量:1
  • 9http://tech. 163. com/16/0229/07/BGVMTL- GA000915BF. html. 被引量:1
  • 10http://nkonst, corn/machine - learning - ex- plained - simple - words/. 被引量:1

二级参考文献15

  • 1Zhao Chumlin, Zheng chong-xun, Zhao Min, et al.. Multivariate autoregressive models and kernel learning algorithms for classifying driving mental fatigue based on electroencephalographic[J]. Expert Systems with Applications, 2011, 38(3): 1859-1865. 被引量:1
  • 2Bengio Y and Delalleuu O. On the expressive power of deep architectures[J]. Lecture Notes in Computer Science, 2011, 6925: 18-36. 被引量:1
  • 3Bengio Y. Deep learning of representations for unsupervised and transfer learning[C]. JMLR: Workshop and Conference Proceedings, Washington, USA, 2012, 27:17- 36. 被引量:1
  • 4Yu D and Li D. Deep learning and its applications to signal and information processing[J]. IEEE Signal Processing Magazine, 2011, 28(1): 145-154. 被引量:1
  • 5Vincent P, Larochelle H, Lajoie I, et al. Stacked denoising autoencoders: learning useful representations in a deep network with a local denoising criterion[J]. Journal of Machine Learning Research, 2010, 11( 2010): 3371-3408. 被引量:1
  • 6Lee T, Mumford D, Romero R, et al.. The role of the primary visual cortex in higher level vision[J]. Vision Research, 1998, 38(15-16): 2429-2454. 被引量:1
  • 7Wong W K and Sun M M. Deep learning regularized fisher mappingsIJ]. IEEE Transactions on Neural Networks, 2011, 22(10): 1668-1675. 被引量:1
  • 8Yah S C, Xu D, Zhang B Y, et al.. Graph embedding and extensions: a general framework for dimensionality reduction [J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2007, 29(1): 40-51. 被引量:1
  • 9Hinton G E and Salakhutdinov R R. Reducing the dimensionality of data with neural networks[J]. Science, 2006, 28,313: 504-507. 被引量:1
  • 10Hinton G E, Osindero S, and Teh Y W. A fast learning algorithm for deep belief nets[J]. Neural Computation, 2006, 18(7): 1527-1554. 被引量:1

共引文献34

同被引文献1007

引证文献130

二级引证文献915

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