187 search results - page 15 / 38 » Bounding the cost of learned rules |
ICML
2010
IEEE
13 years 9 months ago
2010
IEEE
A new procedure for learning cost-sensitive SVM classifiers is proposed. The SVM hinge loss is extended to the cost sensitive setting, and the cost-sensitive SVM is derived as the...
EUROCOLT
1995
Springer
13 years 12 months ago
1995
Springer
k. The model we study can be interpreted as a broad, abstract extension of the well-studied on-line prediction model to a general decision-theoretic setting. We show that the multi...
ICML
2008
IEEE
14 years 9 months ago
2008
IEEE
We propose Laplace max-margin Markov networks (LapM3 N), and a general class of Bayesian M3 N (BM3 N) of which the LapM3 N is a special case with sparse structural bias, for robus...
ICML
2005
IEEE
14 years 9 months ago
2005
IEEE
Mappings to structured output spaces (strings, trees, partitions, etc.) are typically learned using extensions of classification algorithms to simple graphical structures (eg., li...
ICML
2006
IEEE
14 years 9 months ago
2006
IEEE
For a Markov Decision Process with finite state (size S) and action spaces (size A per state), we propose a new algorithm--Delayed Q-Learning. We prove it is PAC, achieving near o...