3668 search results - page 10 / 734 » Margin Distribution and Learning |
JMLR
2006
14 years 9 months ago
2006
Abstract. We give dimension-free and data-dependent bounds for linear multi-task learning where a common linear operator is chosen to preprocess data for a vector of task speci...c...
COLT
2007
Springer
15 years 3 months ago
2007
Springer
This paper analyzes the potential advantages and theoretical challenges of “active learning” algorithms. Active learning involves sequential sampling procedures that use infor...
103
click to vote
ECML
2006
Springer
15 years 1 months ago
2006
Springer
We present a new class of perceptron-like algorithms with margin in which the "effective" learning rate, defined as the ratio of the learning rate to the length of the we...
ACL
2008
14 years 11 months ago
2008
Active learning is a machine learning approach to achieving high-accuracy with a small amount of labels by letting the learning algorithm choose instances to be labeled. Most of p...
COLT
2000
Springer
15 years 1 months ago
2000
Springer
We investigate the computational complexity of the task of detecting dense regions of an unknown distribution from un-labeled samples of this distribution. We introduce a formal l...