278 search results - page 3 / 56 » Strong Separation of Learning Classes |
ICA
2010
Springer
13 years 5 months ago
2010
Springer
We introduce the terms strong sub- and super-Gaussianity to refer to the previously introduced class of densities log-concave is x2 and log-convex in x2 respectively. We derive rel...
CVPR
2009
IEEE
15 years 2 months ago
2009
IEEE
We study the problem of object classification when training
and test classes are disjoint, i.e. no training examples of
the target classes are available. This setup has hardly be...
COLT
2007
Springer
14 years 1 months ago
2007
Springer
For the natural notion of splitting classes into two disjoint subclasses via a recursive classifier working on texts, the question is addressed how these splittings can look in th...
FOCS
1990
IEEE
13 years 11 months ago
1990
IEEE
Two of the most commonly used models in computational learning theory are the distribution-free model in which examples are chosen from a fixed but arbitrary distribution, and the ...
MCS
2010
Springer
14 years 5 days ago
2010
Springer
We have previously described an incremental learning algorithm, Learn++ .NC, for learning from new datasets that may include new concept classes without accessing previously seen d...