Research of stacked denoising sparse autoencoder

doi:10.1007/s00521-016-2790-x

	Research of stacked denoising sparse autoencoder
	Meng, Lingheng 1,2; Ding, Shifei 1,2; Zhang, Nan 1,2; Zhang, Jian 1,2
	2018-10-01
发表期刊	NEURAL COMPUTING & APPLICATIONS
ISSN	0941-0643
卷号	30 期号:7 页码:2083-2100
摘要	Learning results depend on the representation of data, so how to efficiently represent data has been a research hot spot in machine learning and artificial intelligence. With the deepening of the deep learning research, studying how to train the deep networks to express high dimensional data efficiently also has been a research frontier. In order to present data more efficiently and study how to express data through deep networks, we propose a novel stacked denoising sparse autoencoder in this paper. Firstly, we construct denoising sparse autoencoder through introducing both corrupting operation and sparsity constraint into traditional autoencoder. Then, we build stacked denoising sparse autoencoders which has multi-hidden layers by layer-wisely stacking denoising sparse autoencoders. Experiments are designed to explore the influences of corrupting operation and sparsity constraint on different datasets, using the networks with various depth and hidden units. The comparative experiments reveal that test accuracy of stacked denoising sparse autoencoder is much higher than other stacked models, no matter what dataset is used and how many layers the model has. We also find that the deeper the network is, the less activated neurons in every layer will have. More importantly, we find that the strengthening of sparsity constraint is to some extent equal to the increase in corrupted level.
关键词	Autoencoder Stacked autoencoders Feature extraction Unsupervised learning Sparse coding Deep learning
DOI	10.1007/s00521-016-2790-x
收录类别	SCI
语种	英语
资助项目	National Natural Science Foundation of China[61379101] ; National Natural Science Foundation of China[61672522] ; National Basic Research Program of China[2013CB329502]
WOS研究方向	Computer Science
WOS类目	Computer Science, Artificial Intelligence
WOS记录号	WOS:000444953300007
出版者	SPRINGER LONDON LTD
引用统计	被引频次：17[WOS] [WOS记录] [WOS相关记录]
文献类型	期刊论文
条目标识符	http://119.78.100.204/handle/2XEOYT63/4933
专题	中国科学院计算技术研究所期刊论文_英文
通讯作者	Ding, Shifei
作者单位	1.China Univ Min & Technol, Sch Comp Sci & Technol, Xuzhou 221116, Jiangsu, Peoples R China 2.Chinese Acad Sci, Inst Comp Technol, Key Lab Intelligent Informat Proc, Beijing 100190, Peoples R China
推荐引用方式 GB/T 7714	Meng, Lingheng,Ding, Shifei,Zhang, Nan,et al. Research of stacked denoising sparse autoencoder[J]. NEURAL COMPUTING & APPLICATIONS,2018,30(7):2083-2100.
APA	Meng, Lingheng,Ding, Shifei,Zhang, Nan,&Zhang, Jian.(2018).Research of stacked denoising sparse autoencoder.NEURAL COMPUTING & APPLICATIONS,30(7),2083-2100.
MLA	Meng, Lingheng,et al."Research of stacked denoising sparse autoencoder".NEURAL COMPUTING & APPLICATIONS 30.7(2018):2083-2100.