本文已被：浏览 8873次 下载 38770次
Received:December 08, 2015 Revised:January 11, 2016
Received:December 08, 2015 Revised:January 11, 2016
中文摘要: 从2006年开始，深度神经网络在图像/语音识别、自动驾驶等大数据处理和人工智能领域中都取得了巨大成功，其中无监督学习方法作为深度神经网络中的预训练方法为深度神经网络的成功起到了非常重要的作用. 为此，对深度学习中的无监督学习方法进行了介绍和分析，主要总结了两类常用的无监督学习方法，即确定型的自编码方法和基于概率型受限玻尔兹曼机的对比散度等学习方法，并介绍了这两类方法在深度学习系统中的应用，最后对无监督学习面临的问题和挑战进行了总结和展望.
Abstract:Since 2006, Deep Neural Network has achieved huge access in the area of Big Data Processing and Artificial Intelligence, such as image/video discriminations and autopilot. And unsupervised learning methods as the methods getting success in the depth neural network pre training play an important role in deep learning. So, this paper attempts to make a brief introduction and analysis of unsupervised learning methods in deep learning, mainly includs two types, Auto-Encoders based on determination theory and Contrastive Divergence for Restrict Boltzmann Machine based on probability theory. Secondly, the applications of the two methods in Deep Learning are introduced. At last a brief summary and prospect of the challenges faced by unsupervised learning methods in Deep Neural Networks are made.
keywords: auto-encoders restrict boltzmann machine unsupervised learning deep learning neural network
文章编号： 中图分类号： 文献标志码：
基金项目:国家重点基础研究发展计划（973）（2012CB315901）
引用文本：
殷瑞刚,魏帅,李晗,于洪.深度学习中的无监督学习方法综述.计算机系统应用,2016,25(8):1-7
YIN Rui-Gang,WEI Shuai,LI Han,YU Hong.Introduction of Unsupervised Learning Methods in Deep Learning.COMPUTER SYSTEMS APPLICATIONS,2016,25(8):1-7
殷瑞刚,魏帅,李晗,于洪.深度学习中的无监督学习方法综述.计算机系统应用,2016,25(8):1-7
YIN Rui-Gang,WEI Shuai,LI Han,YU Hong.Introduction of Unsupervised Learning Methods in Deep Learning.COMPUTER SYSTEMS APPLICATIONS,2016,25(8):1-7
