摘要
鉴于深度学习的重要性,综述了深度学习的研究进展。首先概述了深度学习具有的优点,由此说明了引入深度学习的必要性;然后描述了三种典型的深度学习模型,包括卷积神经网络模型、深度信任网络模型和堆栈自编码网络模型,并对近几年深度学习在初始化方法、网络层数和激活函数的选择、模型结构、学习算法和实际应用这四个方面的研究新进展进行了综述;最后探讨了深度学习在理论分析、数据表示与模型、特征提取、训练与优化求解和研究拓展这五个方面中有待进一步研究解决的问题。
In view of the significance of deep learning,this paper reviewed the research and development on deep learning.Firstly,this paper summarized the advantage of deep learning,and illustrated the necessity of introducing deep learning. Secondly,it described three kinds of typical deep learning models,included convolutional neural network model,deep belief network model,and stacked auto-encoder network model. Thirdly,it reviewed new research and development on deep learning in recent years,included the choice of initialization methods,the number of network layers,and activation function,model structure,learning algorithms,and practical application. Finally,it presented the problems to be solved in aspects of theoretical analysis,representation and model of data,feature extraction,training and optimization,and research extension.
出处
《计算机应用研究》
CSCD
北大核心
2014年第7期1921-1930,1942,共11页
Application Research of Computers
基金
国家"973"计划资助项目(2012CB720500)
国家自然科学基金资助项目(21006127)
中国石油大学(北京)基础学科研究基金资助项目(JCXK-2011-07)
关键词
深度学习
神经网络
模型
表示
堆栈
预训练
deep learning
neural network
model
representation
stacking
pre-training
