Robust feature learning by stacked autoencoder with maximum correntropy criterion

By Yu Qi, Yueming Wang, Xiaoxiang Zheng, Zhaohui Wu. 2014

83 citations recorded by the source corpus.

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.

Subfields: Computational Mechanics, Computer Vision and Pattern Recognition, Signal Processing

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computational Mechanics

1. Francisco Herrera
2. Salvador Garcia

In Computer Vision and Pattern Recognition

1. Salvador Garcia
2. Francisco Herrera
3. M. J. Jesús
4. Francisco Charte
5. David Charte

In Signal Processing

1. M. J. Jesús
2. Francisco Herrera
3. Francisco Charte
4. David Charte
5. Salvador Garcia
6. Enrique Herrera-Viedma
7. Francisco Chiclana

Citations in the corpus

• A practical tutorial on autoencoders for nonlinear feature fusion: Taxonomy, models, software and guidelines (2018, background): “Robust stacked AEs [73] apply this idea, and manage to be less affected by non-Gaussian noise than standard AEs.”
• Graph Learning: A Survey (2021, unknown): “Auto-encoder [150] is a traditional deep learning model,”