Sciweavers

995 search results - page 106 / 199
» nips 2007
Sort
View
NIPS
2000
15 years 7 months ago
The Manhattan World Assumption: Regularities in Scene Statistics which Enable Bayesian Inference
Preliminary work by the authors made use of the so-called "Manhattan world" assumption about the scene statistics of city and indoor scenes. This assumption stated that ...
James M. Coughlan, Alan L. Yuille
NIPS
2000
15 years 7 months ago
Improved Output Coding for Classification Using Continuous Relaxation
Output coding is a general method for solving multiclass problems by reducing them to multiple binary classification problems. Previous research on output coding has employed, alm...
Koby Crammer, Yoram Singer
NIPS
2000
15 years 7 months ago
Explaining Away in Weight Space
Explaining away has mostly been considered in terms of inference of states in belief networks. We show how it can also arise in a Bayesian context in inference about the weights g...
Peter Dayan, Sham Kakade
NIPS
2000
15 years 7 months ago
A Productive, Systematic Framework for the Representation of Visual Structure
We describe a unified framework for the understanding of structure representation in primate vision. A model derived from this framework is shown to be effectively systematic in t...
Shimon Edelman, Nathan Intrator
NIPS
2000
15 years 7 months ago
On Reversing Jensen's Inequality
Jensen's inequality is a powerful mathematical tool and one of the workhorses in statistical learning. Its applications therein include the EM algorithm, Bayesian estimation ...
Tony Jebara, Alex Pentland