Sciweavers

1376 search results - page 16 / 276
» The Localization Hypothesis and Machines
Sort
View
COLT
1993
Springer
14 years 1 months ago
Learning from a Population of Hypotheses
We introduce a new formal model in which a learning algorithm must combine a collection of potentially poor but statistically independent hypothesis functions in order to approxima...
Michael J. Kearns, H. Sebastian Seung
ICML
2010
IEEE
13 years 11 months ago
Interactive Submodular Set Cover
We introduce a natural generalization of submodular set cover and exact active learning with a finite hypothesis class (query learning). We call this new problem interactive submo...
Andrew Guillory, Jeff Bilmes
ML
2008
ACM
13 years 9 months ago
Large margin vs. large volume in transductive learning
Abstract. We consider a large volume principle for transductive learning that prioritizes the transductive equivalence classes according to the volume they occupy in hypothesis spa...
Ran El-Yaniv, Dmitry Pechyony, Vladimir Vapnik
ICML
2006
IEEE
14 years 10 months ago
Experience-efficient learning in associative bandit problems
We formalize the associative bandit problem framework introduced by Kaelbling as a learning-theory problem. The learning environment is modeled as a k-armed bandit where arm payof...
Alexander L. Strehl, Chris Mesterharm, Michael L. ...
MLCW
2005
Springer
14 years 3 months ago
Recognizing Textual Entailment Via Atomic Propositions
Abstract. This paper describes Macquarie University’s Centre for Language Technology contribution to the PASCAL 2005 Recognizing Textual Entailment challenge. Our main aim was to...
Elena Akhmatova, Diego Mollá