Research Area:  Machine Learning

Abstract:

Deep learning allows automatically learning multiple levels of representations of the underlying distribution of the data to be modeled. In this work, a specific implementation called stacked denoising autoencoders is explored. We contribute by demonstrating that this kind of representation coupled to a SVM improves classification error on MNIST over the usual deep learning approach where a logistic regression layer is added to the stack of denoising autoencoders.

Keywords:  

Author(s) Name:  Francis Quintal Lauzon

Publisher name:  IEEE

DOI:  10.1109/ISSPA.2012.6310529

Volume Information:  

Paper Link:   https://ieeexplore.ieee.org/abstract/document/6310529