Sciweavers

1126 search results - page 97 / 226
» Constraint Classification: A New Approach to Multiclass Clas...
Sort
View
ECML
2003
Springer
14 years 1 months ago
Improving the AUC of Probabilistic Estimation Trees
Abstract. In this work we investigate several issues in order to improve the performance of probabilistic estimation trees (PETs). First, we derive a new probability smoothing that...
César Ferri, Peter A. Flach, José He...
COLT
1998
Springer
14 years 5 days ago
Improved Boosting Algorithms using Confidence-Rated Predictions
Abstract. We describe several improvements to Freund and Schapire's AdaBoost boosting algorithm, particularly in a setting in which hypotheses may assign confidences to each o...
Robert E. Schapire, Yoram Singer
DIS
2006
Springer
13 years 11 months ago
Incremental Algorithm Driven by Error Margins
Incremental learning is an approach to deal with the classification task when datasets are too large or when new examples can arrive at any time. One possible approach uses concent...
Gonzalo Ramos-Jiménez, José del Camp...
MODELLIERUNG
2010
13 years 9 months ago
A Change Metamodel for the Evolution of MOF-Based Metamodels
: The evolution of software systems often produces incompatibilities with existing data and applications. To prevent incompatibilities, changes have to be wellplanned, and develope...
Erik Burger, Boris Gruschko
ICML
2010
IEEE
13 years 9 months ago
Boosting Classifiers with Tightened L0-Relaxation Penalties
We propose a novel boosting algorithm which improves on current algorithms for weighted voting classification by striking a better balance between classification accuracy and the ...
Noam Goldberg, Jonathan Eckstein