17 search results - page 4 / 4 » Classifier Learning with Supervised Marginal Likelihood |
KDD
2002
ACM
14 years 6 months ago
2002
ACM
An adaptive semi-supervised ensemble method, ASSEMBLE, is proposed that constructs classification ensembles based on both labeled and unlabeled data. ASSEMBLE alternates between a...
ICML
2004
IEEE
14 years 6 months ago
2004
IEEE
In many real-world classification problems the input contains a large number of potentially irrelevant features. This paper proposes a new Bayesian framework for determining the r...