An Empirical Evaluation of Deep Architectures on Problems with Many Factors of Variation
Hugo Larochelle - Université de Montréal, Canada
Dumitru Erhan - Université de Montréal, Canada
Aaron Courville - Université de Montréal, Canada
James Bergstra - Université de Montréal, Canada
Yoshua Bengio - Université de Montréal, Canada
Recently, several learning algorithms relying on models with deep architectures have been proposed. Though they have demonstrated impressive performance, to date, they have only been evaluated on relatively simple problems such as digit recognition in a controlled environment, for which many machine learning algorithms already report reasonable results. Here, we present a series of experiments which indicate that these models show promise in solving harder learning problems that exhibit many factors of variation. These models are compared with well-established algorithms such as Support Vector Machines and single hidden-layer feed-forward neural networks.