Convolutional Deep Belief Networks for Scalable Unsupervised Learning of Hierarchical Representations

Authors: Tao Wang, David J. Wu, Adam Coates, Andrew Y. Ng (2012)
AUTHORED BY
Honglak Lee hllee
Roger Grosse rgrosse
Rajesh Ranganath
Andrew Y. Ng

Abstract

There has been much interest in unsuper- vised learning of hierarchical generative mod- els such as deep belief networks. Scaling such models to full-sized, high-dimensional images remains a dicult problem. To ad- dress this problem, we present the convolu- tional deep belief network, a hierarchical gen- erative model which scales to realistic image sizes. This model is translation-invariant and supports ecient bottom-up and top-down probabilistic inference. Key to our approach is probabilistic max-pooling, a novel technique which 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 ob- ject parts, from unlabeled images of objects and natural scenes. We demonstrate excel- lent performance on several visual recogni- tion tasks and show that our model can per- form hierarchical (bottom-up and top-down) inference over full-sized images

Download PDF

Related Projects

Leave a Reply

You must be logged in to post a comment