329 search results - page 21 / 66 » Probably Approximately Correct Learning |
NIPS
2000
13 years 9 months ago
2000
A new incremental learning algorithm is described which approximates the maximal margin hyperplane w.r.t. norm p 2 for a set of linearly separable data. Our algorithm, called alm...
ICML
2003
IEEE
14 years 8 months ago
2003
IEEE
When the goal is to achieve the best correct classification rate, cross entropy and mean squared error are typical cost functions used to optimize classifier performance. However,...
COLT
2007
Springer
14 years 1 months ago
2007
Springer
In the standard model of observational learning, n agents sequentially decide between two alternatives a or b, one of which is objectively superior. Their choice is based on a stoc...
ECML
2007
Springer
14 years 1 months ago
2007
Springer
We describe a novel framework for class noise mitigation that assigns a vector of class membership probabilities to each training instance, and uses the confidence on the current ...
FOCS
1999
IEEE
13 years 12 months ago
1999
IEEE
Mixtures of Gaussians are among the most fundamental and widely used statistical models. Current techniques for learning such mixtures from data are local search heuristics with w...