Deep Belief Networks (DBNs) are hierarchical generative models which have been used successfully to model high dimensional visual data. However, they are not robust to common vari...
In this paper we show that exponentially deep belief networks [3, 7, 4] can approximate any distribution over binary vectors to arbitrary accuracy, even when the width of each lay...
The paper describes two parsing schemes: a shallow approach based on machine learning and a cascaded finite-state parser with a hand-crafted grammar. It discusses several ways to...
The most popular way to use probabilistic models in vision is first to extract some descriptors of small image patches or object parts using well-engineered features, and then to...
This paper reports our recent exploration of the layer-by-layer learning strategy for training a multi-layer generative model of patches of speech spectrograms. The top layer of t...
Li Deng, Michael L. Seltzer, Dong Yu, Alex Acero, ...