Discriminative stacked autoencoder for feature representation and classification  

作　　者：Yiping GAO Xinyu LI Liang GAO 

机构地区：[1]School of Mechanical,Huazhong University of Science and Technology,Wuhan 430072,China

出　　处：《Science China(Information Sciences)》2020年第2期93-94,共2页中国科学（信息科学）（英文版）

基　　金：supported in part by National Natural Science Foundation of China(Grant No.51721092);Natural Science Foundation of Hubei Province(Grant No.2018CFA078);the Program for HUST Academic Frontier Youth Team(Grant No.2017QYTD04).

摘　　要：Dear editor,Recently,deep learning(DL)has become a hot research topic and as one of the most well-known DL models,stacked autoencoder(SAE)[1]has received increasing attention.In SAE,layer-wise pretraining is the basic mechanism for automatic feature extraction and it can also avoid gradient vanishing while constructing deep architectures.

关 键 词：SAE Discriminative stacked autoencoder for FEATURE REPRESENTATION and CLASSIFICATION 

分 类 号：TP18[自动化与计算机技术—控制理论与控制工程]