Research on denoising sparse autoencoder

Lingheng Meng, Shifei Ding, Yu Xue

Research output: Contribution to journalArticleResearchpeer-review

55 Citations (Scopus)

Abstract

Autoencoder can learn the structure of data adaptively and represent data efficiently. These properties make autoencoder not only suit huge volume and variety of data well but also overcome expensive designing cost and poor generalization. Moreover, using autoencoder in deep learning to implement feature extraction could draw better classification accuracy. However, there exist poor robustness and overfitting problems when utilizing autoencoder. In order to extract useful features, meanwhile improve robustness and overcome overfitting, we studied denoising sparse autoencoder through adding corrupting operation and sparsity constraint to traditional autoencoder. The results suggest that different autoencoders mentioned in this paper have some close relation and the model we researched can extract interesting features which can reconstruct original data well. In addition, all results show a promising approach to utilizing the proposed autoencoder to build deep models.

Original languageEnglish
Pages (from-to)1719-1729
Number of pages11
JournalInternational Journal of Machine Learning and Cybernetics
Volume8
Issue number5
DOIs
Publication statusPublished - Oct 2017
Externally publishedYes

Keywords

  • Autoencoder
  • Deep networks
  • Feature extraction
  • Sparse coding
  • Unsupervised learning

Cite this