1080 search results - page 136 / 216 » Hedging predictions in machine learning |
134
click to vote
ECML
2007
Springer
15 years 8 months ago
2007
Springer
Class binarizations are effective methods for improving weak learners by decomposing multi-class problems into several two-class problems. This paper analyzes how these methods can...
150
Voted
ECML
2006
Springer
15 years 8 months ago
2006
Springer
Nearest neighbor forecasting models are attractive with their simplicity and the ability to predict complex nonlinear behavior. They rely on the assumption that observations simila...
129
click to vote
NIPS
2007
15 years 6 months ago
2007
This paper1 explores the use of a Maximal Average Margin (MAM) optimality principle for the design of learning algorithms. It is shown that the application of this risk minimizati...
141
click to vote
EMNLP
2006
15 years 6 months ago
2006
This paper presents a method of automatically constructing information extraction patterns on predicate-argument structures (PASs) obtained by full parsing from a smaller training...
123
click to vote
LWA
2004
15 years 6 months ago
2004
Support Vector Machines (SVMs) have become a popular learning algorithm, in particular for large, high-dimensional classification problems. SVMs have been shown to give most accur...