期刊文献+

深度学习在管理实践中的应用 被引量:4

Application of Deep Learning in Management
下载PDF
导出
摘要 深度学习是近年来学界、业界一个十分热门的话题。在短短几年时间里,深度学习颠覆了语音图像识别、文本理解等众多领域,极大程度上推进了人工智能的快速发展。本文尝试从深度学习的定义与发展历程出发,阐释深度学习的基本原理,并将深度学习与传统的神经网络进行对比。进而,对深度学习的几种常见方法进行系统性归类阐述,并对接了行业研究的最新现状。文章的最后,对深度学习在管理实践当中的应用及深度学习带来的变革与挑战进行了发散性讨论。 Deep learning is a hot topic in no only academic but also business area in recent years, deep learning has overturned many areas such as speech image recognition and text understanding, and has greatly promoted the rapid development of artificial intelligence, in just a few days. This paper begins with the definition and development of deep learning, explains the basic principles of deep learning, and compares deep learning with traditional neural networks. Further, this paper systematically categorizes several common methods of deep learning and correlates the latest tensions in industry research. At the end of the paper, a divergent discussion was held about the application of deep learning in management practices and the changes and challenges brought about by deep learning.
作者 肖泽中 Xiao Zezhong(Renmin University of China,Beijing 100872,China)
机构地区 中国人民大学
出处 《未来与发展》 2018年第9期57-63,共7页 Future and Development
关键词 深度学习 神经网络 分类 训练 deep learning neural network classification training
  • 相关文献

参考文献3

二级参考文献95

  • 1叶世伟,史忠植.神经网络原理[M].北京:机械工业出版社,2006.
  • 2史忠值.神经网络[M].北京:高等教育出版社,2009.
  • 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.
  • 4Haykin S. Neural Networks and Learning Machines (3rd Edition) [M]. New Jersey: Pearson Education, 2009.
  • 5Hinton G E, Sejnowski T J. Learning and relearning in Boltzmann machines[C]// Parallel Distributed Processing: Explorations in the Microstructure of Cognition,Cambridge, USA, 1986.
  • 6Smolensky P. Information processing in dynamical systems: foundations of harmony theory[C]// Parallel Distributed Processing: Explorations in the Microstructure of Cognition, Cambridge, USA, 1986.
  • 7Freund Y, Haussler D. Unsupervised learning of distributions on binary vectors using two layer networks[R]. Santa Cruz: University of California, UCSC-CRL-94-25, 1994.
  • 8Roux N L, Bengio Y. Representational power of restricted Boltzmann machines and deep belief networks[J]. Neural Computation, 2008,20(6): 1631-1649.
  • 9Hinton G E. Training products of experts by minimizing contrastive divergence [J]. Neural Computation, 2002, 14(8): 1771-1800.
  • 10Cho K Y. Improved learning algorithms for restricted Boltzmann machines[D]. Espoo: Aalto University,2011.

共引文献308

同被引文献16

引证文献4

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