中国科学院机构知识库网格
Chinese Academy of Sciences Institutional Repositories Grid
首页 机构 成果 学者
  
  1. CAS IR Grid
  2. 计算技术研究所
  3. 中国科学院计算技术研究所
  4. 中国科学院计算技术研究所期刊论文
  5. 英文
Research of stacked denoising sparse autoencoder

文献类型：期刊论文

作者Meng, Lingheng1,2; Ding, Shifei1,2; Zhang, Nan1,2; Zhang, Jian1,2
刊名NEURAL COMPUTING & APPLICATIONS
出版日期2018-10-01
卷号30期号:7页码:2083-2100
关键词Autoencoder Stacked autoencoders Feature extraction Unsupervised learning Sparse coding Deep learning
ISSN号0941-0643
DOI10.1007/s00521-016-2790-x
英文摘要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.
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
语种英语
WOS记录号WOS:000444953300007
出版者SPRINGER LONDON LTD
源URL[http://119.78.100.204/handle/2XEOYT63/4932]  
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.

入库方式： OAI收割

来源：计算技术研究所

浏览0
下载0
收藏0
其他版本

除非特别说明，本系统中所有内容都受版权保护，并保留所有权利。