Sciweavers

11 search results - page 1 / 3
» Using Deep Belief Nets to Learn Covariance Kernels for Gauss...
Sort
View
NIPS
2007
13 years 5 months ago
Using Deep Belief Nets to Learn Covariance Kernels for Gaussian Processes
We show how to use unlabeled data and a deep belief net (DBN) to learn a good covariance kernel for a Gaussian process. We first learn a deep generative model of the unlabeled da...
Ruslan Salakhutdinov, Geoffrey E. Hinton
JMLR
2010
169views more  JMLR 2010»
12 years 10 months ago
Factored 3-Way Restricted Boltzmann Machines For Modeling Natural Images
Deep belief nets have been successful in modeling handwritten characters, but it has proved more difficult to apply them to real images. The problem lies in the restricted Boltzma...
Marc'Aurelio Ranzato, Alex Krizhevsky, Geoffrey E....
NIPS
2004
13 years 5 months ago
Learning Gaussian Process Kernels via Hierarchical Bayes
We present a novel method for learning with Gaussian process regression in a hierarchical Bayesian framework. In a first step, kernel matrices on a fixed set of input points are l...
Anton Schwaighofer, Volker Tresp, Kai Yu
ICASSP
2011
IEEE
12 years 7 months ago
Deep belief nets for natural language call-routing
This paper considers application of Deep Belief Nets (DBNs) to natural language call routing. DBNs have been successfully applied to a number of tasks, including image, audio and ...
Ruhi Sarikaya, Geoffrey E. Hinton, Bhuvana Ramabha...
JMLR
2010
202views more  JMLR 2010»
12 years 10 months ago
Learning the Structure of Deep Sparse Graphical Models
Deep belief networks are a powerful way to model complex probability distributions. However, it is difficult to learn the structure of a belief network, particularly one with hidd...
Ryan Prescott Adams, Hanna M. Wallach, Zoubin Ghah...