801 search results - page 112 / 161 » Machine Learning with Data Dependent Hypothesis Classes |
JMLR
2010
13 years 3 months ago
2010
Supervised learning from multiple labeling sources is an increasingly important problem in machine learning and data mining. This paper develops a probabilistic approach to this p...
ICML
2009
IEEE
14 years 9 months ago
2009
IEEE
Information theoretic based measures form a fundamental class of similarity measures for comparing clusterings, beside the class of pair-counting based and set-matching based meas...
ICML
2006
IEEE
14 years 9 months ago
2006
IEEE
We present a new approach to personalized handwriting recognition. The problem, also known as writer adaptation, consists of converting a generic (user-independent) recognizer int...
ICML
2005
IEEE
14 years 9 months ago
2005
IEEE
Given a classification problem, our goal is to find a low-dimensional linear transformation of the feature vectors which retains information needed to predict the class labels. We...
ECML
2007
Springer
14 years 2 months ago
2007
Springer
Boosting methods are known to exhibit noticeable overfitting on some datasets, while being immune to overfitting on other ones. In this paper we show that standard boosting algorit...