Get 20M+ Full-Text Papers For Less Than $1.50/day. Start a 14-Day Trial for You or Your Team.

Learn More →

Research on denoising sparse autoencoder

Research on denoising sparse autoencoder 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. http://www.deepdyve.com/assets/images/DeepDyve-Logo-lg.png International Journal of Machine Learning and Cybernetics Springer Journals

Loading next page...
1
 
/lp/springer_journal/research-on-denoising-sparse-autoencoder-BHpvRuoZiA

References (38)

Publisher
Springer Journals
Copyright
Copyright © 2016 by Springer-Verlag Berlin Heidelberg
Subject
Engineering; Computational Intelligence; Artificial Intelligence (incl. Robotics); Control, Robotics, Mechatronics; Complex Systems; Systems Biology; Pattern Recognition
ISSN
1868-8071
eISSN
1868-808X
DOI
10.1007/s13042-016-0550-y
Publisher site
See Article on Publisher Site

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.

Journal

International Journal of Machine Learning and CyberneticsSpringer Journals

Published: May 31, 2016

There are no references for this article.