FLAIRS
1998
13 years 5 months ago
1998
Manual generation of training examples for supervised learning is an expensive process. One way to reduce this cost is to produce training instances that are highly informative. T...
ACML
2009
Springer
13 years 9 months ago
2009
Springer
A fundamental assumption for any machine learning task is to have training and test data instances drawn from the same distribution while having a sufficiently large number of tra...
COLT
2005
Springer
13 years 10 months ago
2005
Springer
We discuss a simple sparse linear problem that is hard to learn with any algorithm that uses a linear combination of the training instances as its weight vector. The hardness holds...
AWIC
2007
Springer
13 years 10 months ago
2007
Springer
A major difficulty of supervised approaches for text classification is that they require a great number of training instances in order to construct an accurate classifier. This pap...
ICDM
2008
IEEE
13 years 10 months ago
2008
IEEE
In this paper, we propose the "Democratic Classifier", a simple, democracy-inspired patternbased classification algorithm that uses very short patterns for classificatio...
ICML
2006
IEEE
14 years 5 months ago
2006
IEEE
Support Vector Machines (SVMs) suffer from an O(n2 ) training cost, where n denotes the number of training instances. In this paper, we propose an algorithm to select boundary ins...