期刊文献+

深度学习算法与应用探究 被引量:2

On the Algorithm and Application of Deep Learning
下载PDF
导出
摘要 首先对浅层结构经典算法易出现局部最优和过度拟合状况做了分析、归纳.其次,对深度学习现状做了阐述,详细介绍基于RBM和AE算法的深度模型,并对深度学习在智能语音、机器视觉图像、点击通过率、逻辑回归模型、自然语言以及视频动作识别等方面应用作了介绍,表明深度学习相对于其它模型结构优势明显,对深度学习的理论以及应用的研究有重要意义.最后对深度学习当前研究存在的问题进行简要归纳总结,并对模型结构未来研究方向做了探究. Firstly, this thesis analyzes and summarizes the local optimum and over fitting which are likely to occur in classic surface structure algorithm. Secondly, this thesis illustrates the current situa- tion of deep learning and gives a detailed introduction of deep model based on RBM and AE algorithm. Thirdly, this thesis introduces the application of deep learning in recent years in terms of intelligent voice, machine vision image, click- through rates, logistic regression model, natural language and video motion recognition, etc. and demonstrates the obvious advantages o{ deep learning over other model structures, which has great significance in promoting the research on the theory and application of deep learning. Finally, this thesis summarizes the problems of current research on deep learning briefly and explores the future direction of model structure research.
作者 韩俊波 HAN Junbo(Institute of Information Engineering,Chaohu College, Chaohu 238000, Anhu)
出处 《湖州师范学院学报》 2016年第10期48-53,共6页 Journal of Huzhou University
基金 巢湖学院科研支持项目(XLY-201614)
关键词 浅层结构 深度学习 算法 模型结构 shallow structure deep learning algorithm model structure
  • 相关文献

参考文献7

二级参考文献242

  • 1史忠值.神经网络[M].北京:高等教育出版社,2009.
  • 2BENGIO Y, DELALLEAU O. On the expressive power of deep archi- tectures[ C ]//Proc of the 14th International Conference on Discovery Science. Berlin : Springer-Verlag, 2011 : 18 - 36.
  • 3BENGIO Y. Leaming deep architectures for AI[ J]. Foundations and Trends in Machine Learning ,2009,2 ( 1 ) : 1-127.
  • 4HINTON G,OSINDERO S,TEH Y. A fast learning algorithm for deep belief nets [ J ]. Neural Computation ,2006,18 (7) : 1527-1554.
  • 5BENGIO Y, LAMBLIN P, POPOVICI D, et al. Greedy layer-wise training of deep networks [ C ]//Proc of the 12th Annual Conference on Neural Information Processing System. 2006:153-160.
  • 6LECUN Y, BOTTOU L, BENGIO Y, et al. Gradient-based learning ap- plied to document recognition[ J]. Proceedings of the iEEE, 1998, 86( 11 ) :2278-2324.
  • 7VINCENT P, LAROCHELLE H, BENGIO Y, et al. Extracting and composing robust features with denoising autoencoders[ C ]//Proc of the 25th International Conference on Machine Learning. New York: ACM Press ,2008 : 1096-1103.
  • 8VINCENT P, LAROCHELLE H, LAJOIE I, et aL Stacked denoising autoencoders:learning useftd representations in a deep network with a local denoising criterion [ J ]. Journal of Machine Learning Re- search ,2010,11 ( 12 ) :3371-3408.
  • 9YU Dong, DENG Li. Deep convex net: a scalable architecture for speech pattern classification [ C]//Proc of the 12th Annual Confe-rence of International Speech Comunication Association. 2011 : 2285- 2288.
  • 10POON H, DOMINGOS P. Sum-product networks:a new deep architec- ture[ C ]//Proc of IEEE Intemational Conference on Computer Vi- sion. 2011:689-690.

共引文献1750

同被引文献32

引证文献2

二级引证文献5

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