An introduction to deep learning

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.

# Neural Networks and Applications # Computer Science # Stochastic Gradient Optimization Techniques # Machine Learning and Data Classification

Francis Quintal Lauzon (2012). "An introduction to deep learning". International Conference on Information Science, Signal Processing and their Applications (ISSPA). https://doi.org/10.1109/isspa.2012.6310529