DocumentCode :
2771245
Title :
Model Selection in an Ensemble Framework
Author :
Wichard, Jörg D.
Author_Institution :
Schering AG, Berlin and the Institute of Molecular Pharmacology Molecular Modelling Group, Robert Rössle Straβe 10, D-13125 Berlin-Buch, Germany. email: JoergWichard@web.de
fYear :
2006
fDate :
16-21 July 2006
Firstpage :
2187
Lastpage :
2192
Abstract :
We like to present a method to build ensemble models based on an extended cross-validation approach. The cross-validation puts several model classes in a tournament and selects the best performing model with respect to the validation set. This leads to a model selection strategy and an estimation of the expected modelling error.
Keywords :
Decision trees; Neural networks; Predictive models; Stability; Supervised learning; Testing; Training data;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Neural Networks, 2006. IJCNN '06. International Joint Conference on
Print_ISBN :
0-7803-9490-9
Type :
conf
DOI :
10.1109/IJCNN.2006.247012
Filename :
1716382
Link To Document :
بازگشت