Sciweavers

351 search results - page 65 / 71
» Estimating Linear Models for Compositional Distributional Se...
Sort
View
ICML
2010
IEEE
13 years 8 months ago
Restricted Boltzmann Machines are Hard to Approximately Evaluate or Simulate
Restricted Boltzmann Machines (RBMs) are a type of probability model over the Boolean cube {-1, 1}n that have recently received much attention. We establish the intractability of ...
Philip M. Long, Rocco A. Servedio
WSDM
2010
ACM
213views Data Mining» more  WSDM 2010»
14 years 5 months ago
Corroborating Information from Disagreeing Views
We consider a set of views stating possibly conflicting facts. Negative facts in the views may come, e.g., from functional dependencies in the underlying database schema. We want ...
Alban Galland, Serge Abiteboul, Amélie Mari...
ICPR
2010
IEEE
13 years 6 months ago
3D Vertebrae Segmentation in CT Images with Random Noises
Exposure levels (X-ray tube amperage and peak kilovoltage) are associated with various noise levels and radiation dose. When higher exposure levels are applied, the images have hi...
Melih Seref Aslan
MICCAI
2006
Springer
14 years 8 months ago
The Entire Regularization Path for the Support Vector Domain Description
Abstract. The support vector domain description is a one-class classification method that estimates the shape and extent of the distribution of a data set. This separates the data ...
Karl Sjöstrand, Rasmus Larsen
ECCV
2010
Springer
14 years 23 days ago
Weakly Supervised Shape Based Object Detection with Particle Filter
Abstract. We describe an efficient approach to construct shape models composed of contour parts with partially-supervised learning. The proposed approach can easily transfer parts ...