Work

Unsupervised learning of hierarchical representations with convolutional deep belief networks

Year: 2011

Type: article

Abstract: There has been much interest in unsupervised learning of hierarchical generative models such as deep belief networks (DBNs); however, scaling such models to full-sized, high-dimensional images remains a difficult problem. To address this problem, we present the convolutional deep belief network , a hierarchical generative model that scales to realistic image sizes. This model is translation-invariant and supports efficient bottom-up and top-down probabilistic inference. Key to our approach is probabilistic max-pooling , a novel technique that shrinks the representations of higher layers in a probabilistically sound way. Our experiments show that the algorithm learns useful high-level visual features, such as object parts, from unlabeled images of objects and natural scenes. We demonstrate excellent performance on several visual recognition tasks and show that our model can perform hierarchical (bottom-up and top-down) inference over full-sized images.

Source: Communications of the ACM

DOI: 10.1145/2001269.2001295

Authors: Honglak Lee, Roger Grosse, Rajesh Ranganath, Andrew Y. Ng

Institutions: University of Michigan, MIT Computer Science and Artificial Intelligence Laboratory, Massachusetts Institute of Technology, Stanford University

Language: English

Topic: Advanced Neural Network Applications

Subfield: Computer Vision and Pattern Recognition

Field: Computer Science

Domain: Physical Sciences

Open Access status: bronze

Funder: Defense Advanced Research Projects Agency

Award: G440206934