4903 search results - page 591 / 981 » The Set Covering Machine |
166
click to vote
KDD
2005
ACM
16 years 7 months ago
2005
ACM
In the paper we show that diagnostic classes in cancer gene expression data sets, which most often include thousands of features (genes), may be effectively separated with simple ...
169
Voted
ECML
2001
Springer
15 years 11 months ago
2001
Springer
Labeled data for classification could often be obtained by sampling that restricts or favors choice of certain classes. A classifier trained using such data will be biased, resulti...
166
click to vote
COLT
1999
Springer
15 years 11 months ago
1999
Springer
The empirical error on a test set, the hold-out estimate, often is a more reliable estimate of generalization error than the observed error on the training set, the training estim...
168
click to vote
COLT
1997
Springer
15 years 11 months ago
1997
Springer
We relate two problems that have been explored in two distinct communities. The first is the problem of combining expert advice, studied extensively in the computational learning...
198
click to vote
COLT
2005
Springer
15 years 8 months ago
2005
Springer
External regret compares the performance of an online algorithm, selecting among N actions, to the performance of the best of those actions in hindsight. Internal regret compares ...