Sciweavers

536 search results - page 84 / 108
» Residual Algorithms: Reinforcement Learning with Function Ap...
Sort
View
CVPR
2007
IEEE
14 years 9 months ago
What makes a good model of natural images?
Many low-level vision algorithms assume a prior probability over images, and there has been great interest in trying to learn this prior from examples. Since images are very non G...
Yair Weiss, William T. Freeman
FOCS
2002
IEEE
14 years 18 days ago
Learning Intersections and Thresholds of Halfspaces
We give the first polynomial time algorithm to learn any function of a constant number of halfspaces under the uniform distribution on the Boolean hypercube to within any constan...
Adam Klivans, Ryan O'Donnell, Rocco A. Servedio
CVPR
2008
IEEE
14 years 9 months ago
Conditional density learning via regression with application to deformable shape segmentation
Many vision problems can be cast as optimizing the conditional probability density function p(C|I) where I is an image and C is a vector of model parameters describing the image. ...
Jingdan Zhang, Shaohua Kevin Zhou, Dorin Comaniciu...
IJON
2007
184views more  IJON 2007»
13 years 7 months ago
Convex incremental extreme learning machine
Unlike the conventional neural network theories and implementations, Huang et al. [Universal approximation using incremental constructive feedforward networks with random hidden n...
Guang-Bin Huang, Lei Chen
UAI
2008
13 years 9 months ago
Learning Arithmetic Circuits
Graphical models are usually learned without regard to the cost of doing inference with them. As a result, even if a good model is learned, it may perform poorly at prediction, be...
Daniel Lowd, Pedro Domingos