Sciweavers

163 search results - page 23 / 33
» Learning universal probabilistic models for fault localizati...
Sort
View
NECO
2008
170views more  NECO 2008»
13 years 7 months ago
Representational Power of Restricted Boltzmann Machines and Deep Belief Networks
Deep Belief Networks (DBN) are generative neural network models with many layers of hidden explanatory factors, recently introduced by Hinton et al., along with a greedy layer-wis...
Nicolas Le Roux, Yoshua Bengio
FECS
2007
184views Education» more  FECS 2007»
13 years 9 months ago
Collaboratory: An Open Source Teaching and Learning Facility for Computer Science and Engineering Education
In this paper we present an innovative prototype Open Source Teaching/Learning Collaboratory created at UC Merced that will provide the foundation for offering the vast majority of...
Jeff Wright, Stefano Carpin, Alberto Cerpa, German...
ICCV
1999
IEEE
13 years 12 months ago
Learning Low-Level Vision
We describe a learning-based method for low-level vision problems--estimating scenes from images. We generate a synthetic world of scenes and their corresponding rendered images, m...
William T. Freeman, Egon C. Pasztor
PAMI
2007
187views more  PAMI 2007»
13 years 7 months ago
Supervised Learning of Semantic Classes for Image Annotation and Retrieval
—A probabilistic formulation for semantic image annotation and retrieval is proposed. Annotation and retrieval are posed as classification problems where each class is defined as...
Gustavo Carneiro, Antoni B. Chan, Pedro J. Moreno,...
UAI
2003
13 years 9 months ago
The Information Bottleneck EM Algorithm
Learning with hidden variables is a central challenge in probabilistic graphical models that has important implications for many real-life problems. The classical approach is usin...
Gal Elidan, Nir Friedman