Logo 知识与财富的链接
深度学习研究综述

深度学习研究综述

ISSN:1001-3695
2012年第29卷第8期
综述评论
孙志军1,薛磊2,许阳明2,王正2 SUN Zhi-jun[1] , XUE Lei[2] , XU Yang-ming[2] , WANG Zheng[2]
  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
SUN Zhi-jun 1,XUE Lei 1,2,XU Yang-ming 1,2,WANG Zheng 1,2(1.Electronic Engineering Institute,Hefei 230037,China;2.Key Laboratory of Electronic Restriction,Hefei 230037,China)

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.

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.

认领
收 藏
点 赞
认领进度
0 %

发表评论

ISSN:1001-3695
2012年第29卷第8期
综述评论

用户信息设置