Computer Science – Learning
Scientific paper
2007-06-25
ASMDA 2007 (2007) 1-8
Computer Science
Learning
Scientific paper
Bounds on the risk play a crucial role in statistical learning theory. They usually involve as capacity measure of the model studied the VC dimension or one of its extensions. In classification, such "VC dimensions" exist for models taking values in {0, 1}, {1,..., Q} and R. We introduce the generalizations appropriate for the missing case, the one of models with values in R^Q. This provides us with a new guaranteed risk for M-SVMs which appears superior to the existing one.
No associations
LandOfFree
Scale-sensitive Psi-dimensions: the Capacity Measures for Classifiers Taking Values in R^Q does not yet have a rating. At this time, there are no reviews or comments for this scientific paper.
If you have personal experience with Scale-sensitive Psi-dimensions: the Capacity Measures for Classifiers Taking Values in R^Q, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Scale-sensitive Psi-dimensions: the Capacity Measures for Classifiers Taking Values in R^Q will most certainly appreciate the feedback.
Profile ID: LFWR-SCP-O-230517