801 search results - page 6 / 161 » Machine Learning with Data Dependent Hypothesis Classes |
ICANN
2009
Springer
14 years 1 days ago
2009
Springer
This paper proposes a modelling of Support Vector Machine (SVM) learning to address the problem of learning with sloppy labels. In binary classification, learning with sloppy labe...
ICML
2010
IEEE
13 years 8 months ago
2010
IEEE
We introduce a natural generalization of submodular set cover and exact active learning with a finite hypothesis class (query learning). We call this new problem interactive submo...
FUIN
2008
13 years 7 months ago
2008
Abstract. This work extends studies of Angluin, Lange and Zeugmann on how learnability of a language class depends on the hypothesis space used by the learner. While previous studi...
CORR
2006
Springer
13 years 7 months ago
2006
Springer
Abstract. We propose and analyze a new vantage point for the learning of mixtures of Gaussians: namely, the PAC-style model of learning probability distributions introduced by Kear...
EUROCOLT
1997
Springer
13 years 11 months ago
1997
Springer
The approach of ordinal mind change complexity, introduced by Freivalds and Smith, uses (notations for) constructive ordinals to bound the number of mind changes made by a learnin...