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.

Keywords

Computer scienceVariation (astronomy)Deep learningArtificial intelligenceMachine learningArtificial neural networkSeries (stratigraphy)Simple (philosophy)Support vector machine

Affiliated Institutions

Related Publications

Publication Info

Year
2007
Type
article
Pages
473-480
Citations
1021
Access
Closed

External Links

View on DOI.org

Social Impact

Altmetric
PlumX Metrics

Social media, news, blog, policy document mentions

Citation Metrics

1021
OpenAlex

Cite This

Hugo Larochelle, Dumitru Erhan, Aaron Courville et al. (2007). An empirical evaluation of deep architectures on problems with many factors of variation. , 473-480. https://doi.org/10.1145/1273496.1273556

Identifiers

DOI
10.1145/1273496.1273556