Unsupervised learning of hierarchical representations with convolutional deep belief networks
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.
Document Details
- Document Type
- Pub Defense Publication
- Publication Date
- Oct 01, 2011
- Source ID
- 10.1145/2001269.2001295
Entities
People
- Andrew Y. Ng
- Honglak Lee
- Rajesh Ranganath
- Roger Grosse
Organizations
- Defense Advanced Research Projects Agency
- Massachusetts Institute of Technology
- Stanford University
- University of Michigan