SCIENCE CHINA Information Sciences, Volume 63 , Issue 2 : 120111(2020) https://doi.org/10.1007/s11432-019-2722-3

Discriminative stacked autoencoder for feature representation and classification

More info
  • ReceivedAug 10, 2019
  • AcceptedNov 1, 2019
  • PublishedJan 14, 2020


There is no abstract available for this article.


This work was supported in part by National Natural Science Foundation of China (Grant No. 51721092), Natural Science Foundation of Hubei Province (Grant No. 2018CFA078), and the Program for HUST Academic Frontier Youth Team (Grant No. 2017QYTD04).


[1] Hinton G E. Reducing the dimensionality of data with neural networks.. Science, 2006, 313: 504-507 CrossRef PubMed Google Scholar

[2] Gao Y, Gao L, Li X. A zero-shot learning method for fault diagnosis under unknown working loads. J Intell Manuf, 2019, 3 CrossRef Google Scholar

[3] Mehta J, Majumdar A. RODEO: Robust DE-aliasing autoencOder for real-time medical image reconstruction. Pattern Recognition, 2017, 63: 499-510 CrossRef Google Scholar

[4] Zhu Z, Wang X, Bai S. Deep Learning Representation using Autoencoder for 3D Shape Retrieval. Neurocomputing, 2016, 204: 41-50 CrossRef Google Scholar

[5] Fan Y J. Autoencoder node saliency: selecting relevant latent representations. Pattern Recogn, 2019, 88: 643--653. Google Scholar

  • Figure 1

    (Color online) (a) The diagram of the proposed DSA. (b) The data visualization of the learned feature; the top shows the feature learned from the original SAE, and the bottom is the feature learned from the proposed DSA.