Sciweavers

278 search results - page 29 / 56
» Strong Separation of Learning Classes
Sort
View
115
Voted
CVPR
2008
IEEE
15 years 9 months ago
Partitioning of image datasets using discriminative context information
We propose a new method to partition an unlabeled dataset, called Discriminative Context Partitioning (DCP). It is motivated by the idea of splitting the dataset based only on how...
Christoph H. Lampert
102
Voted
AAAI
1994
15 years 3 months ago
Learning to Reason
We introduce a new framework for the study of reasoning. The Learning (in order) to Reason approach developed here views learning as an integral part of the inference process, and ...
Roni Khardon, Dan Roth
115
Voted
FOCS
2008
IEEE
15 years 9 months ago
Almost-Natural Proofs
Razborov and Rudich have shown that so-called natural proofs are not useful for separating P from NP unless hard pseudorandom number generators do not exist. This famous result is...
Timothy Y. Chow
ICML
2010
IEEE
15 years 2 months ago
Application of Machine Learning To Epileptic Seizure Detection
We present and evaluate a machine learning approach to constructing patient-specific classifiers that detect the onset of an epileptic seizure through analysis of the scalp EEG, a...
Ali H. Shoeb, John V. Guttag
158
Voted
CVPR
2009
IEEE
16 years 9 months ago
Visual Tracking with Online Multiple Instance Learning
In this paper, we address the problem of learning an adaptive appearance model for object tracking. In particular, a class of tracking techniques called “tracking by detectionâ...
Boris Babenko, Ming-Hsuan Yang, Serge J. Belongie