Robust feature learning by stacked autoencoder with maximum correntropy criterion

Yu Qi, Yueming Wang, Xiaoxiang Zheng, Zhaohui WuICASSP 2014 · OpenReview

Abstract

Unsupervised feature learning with deep networks has been widely studied in the recent years. Despite the progress, most existing models would be fragile to non-Gaussian noises and outliers due to the criterion of mean square error (MSE). In this paper, we propose a robust stacked autoencoder (R-SAE) based on maximum correntropy criterion (MCC) to deal with the data containing non-Gaussian noises and outliers. By replacing MSE with MCC, the anti-noise ability of stacked autoencoder is improved. The proposed method is evaluated using the MNIST benchmark dataset. Experimental results show that, compared with the ordinary stacked autoencoder, the R-SAE improves classification accuracy by 14% and reduces the reconstruction error by 39%, which demonstrates that R-SAE is capable of learning robust features on noisy data.
BibTeX
@inproceedings{qi2014robust,
  author = {Yu Qi and Yueming Wang and Xiaoxiang Zheng and Zhaohui Wu},
  title = {{Robust feature learning by stacked autoencoder with maximum correntropy criterion}},
  booktitle = {IEEE International Conference on Acoustics, Speech and Signal Processing},
  year = {2014},
  url = {https://openreview.net/forum?id=AA2KswJWoc},
}

Loading related content...

Figure