701 search results - page 79 / 141 » Self Bounding Learning Algorithms |
COLT
2010
Springer
13 years 5 months ago
2010
Springer
We investigate the problem of active learning on a given tree whose nodes are assigned binary labels in an adversarial way. Inspired by recent results by Guillory and Bilmes, we c...
COLT
1997
Springer
13 years 12 months ago
1997
Springer
The problem of learning linear discriminant concepts can be solved by various mistake-driven update procedures, including the Winnow family of algorithms and the well-known Percep...
ALT
1999
Springer
13 years 12 months ago
1999
Springer
We introduce a new model for learning in the presence of noise, which we call the Nasty Noise model. This model generalizes previously considered models of learning with noise. Th...
ICML
2005
IEEE
14 years 8 months ago
2005
IEEE
We consider online learning where the target concept can change over time. Previous work on expert prediction algorithms has bounded the worst-case performance on any subsequence ...
ECCV
2002
Springer
14 years 9 months ago
2002
Springer
Numerous statistical learning methods have been developed for visual recognition tasks. Few attempts, however, have been made to address theoretical issues, and in particular, stud...