首页 | 本学科首页   官方微博 | 高级检索  
     

深度学习研究综述
引用本文:孙志军,薛 磊,许阳明,王 正.深度学习研究综述[J].计算机应用研究,2012,29(8):2806-2810.
作者姓名:孙志军  薛 磊  许阳明  王 正
作者单位:1. 电子工程学院,合肥,230037
2. 电子工程学院,合肥230037;安徽省电子制约技术重点实验室,合肥230037
摘    要:深度学习是一类新兴的多层神经网络学习算法,因其缓解了传统训练算法的局部最小性,引起机器学习领域的广泛关注。首先论述了深度学习兴起渊源,分析了算法的优越性,并介绍了主流学习算法及应用现状,最后总结了当前存在的问题及发展方向。

关 键 词:深度学习  分布式表示  深信度网络  卷积神经网络  深凸网络

Overview of deep learning
SUN Zhi-jun,XUE Lei,XU Yang-ming,WANG Zheng.Overview of deep learning[J].Application Research of Computers,2012,29(8):2806-2810.
Authors:SUN Zhi-jun  XUE Lei  XU Yang-ming  WANG Zheng
Affiliation:1. Electronic Engineering Institute, Hefei 230037, China; 2. Key Laboratory of Electronic Restriction, Hefei 230037, China
Abstract:Deep learning is a new way of training multi-layer neural network. The optimization difficulty associated with the deep models can be alleviated, it has induced great attention of machine learning community. Firstly, this paper discussed the origin of deep learning, then analyzed virtue brought by deep learning. It introduced the main stream deep learning algorithm and their applications. Finally it concluded the problem remaining and development orientation.
Keywords:deep learning  distributed representation  deep belief network  convolutional neural network  deep convex network
本文献已被 CNKI 万方数据 等数据库收录!
点击此处可从《计算机应用研究》浏览原始摘要信息
点击此处可从《计算机应用研究》下载全文
设为首页 | 免责声明 | 关于勤云 | 加入收藏

Copyright©北京勤云科技发展有限公司  京ICP备09084417号