329 search results - page 44 / 66 » Probably Approximately Correct Learning |
109
Voted
ECAI
2004
Springer
15 years 6 months ago
2004
Springer
Instance-based learning (IBL) algorithms have proved to be successful in many applications. However, as opposed to standard statistical methods, a prediction in IBL is usually give...
153
Voted
DAGM
2008
Springer
15 years 4 months ago
2008
Springer
Three-dimensional electron-microscopic image stacks with almost isotropic resolution allow, for the first time, to determine the complete connection matrix of parts of the brain. I...
105
Voted
FOCS
2009
IEEE
15 years 9 months ago
2009
IEEE
— We prove the following strong hardness result for learning: Given a distribution on labeled examples from the hypercube such that there exists a monomial (or conjunction) consi...
139
Voted
WSC
2007
15 years 5 months ago
2007
Statistical selection procedures can identify the best of a finite set of alternatives, where “best” is defined in terms of the unknown expected value of each alternative’...
119
Voted
IJAR
2010
14 years 12 months ago
2010
In this paper we present TANC, i.e., a tree-augmented naive credal classifier based on imprecise probabilities; it models prior near-ignorance via the Extreme Imprecise Dirichlet ...