深度学习研究综述  

Overview of deep learning

作　　者：孙志军[1] 薛磊[1,2] 许阳明[1,2] 王正[1,2] 

机构地区：[1]电子工程学院,合肥230037 [2]安徽省电子制约技术重点实验室,合肥230037

出　　处：《计算机应用研究》2012年第8期2806-2810,共5页Application Research of Computers

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。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.

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 

分 类 号：TP181[自动化与计算机技术—控制理论与控制工程]