An empirical evaluation of deep architectures on problems with many factors of variation

Hugo Larochelle, Dumitru Erhan, Aaron C. Courville, James Bergstra, Yoshua Bengio

Abstract

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.
BibTeX
@inproceedings{larochelle2007empirical,
  author = {Hugo Larochelle and Dumitru Erhan and Aaron C. Courville and James Bergstra and Yoshua Bengio},
  title = {{An empirical evaluation of deep architectures on problems with many factors of variation}},
  booktitle = {International Conference on Machine Learning},
  year = {2007},
  doi = {10.1145/1273496.1273556},
}

Loading related content...

Figure