An introduction to deep learning
Francis Quintal Lauzon · 2012
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.