PT Unknown
AU Miguel Angel Bautista
   Xavier Baro
   Oriol Pujol
   Petia Radeva
   Jordi Vitria
   Sergio Escalera
TI Compact Evolutive Design of Error-Correcting Output Codes
BT Supervised and Unsupervised Ensemble Methods and their Applications in the European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases
PY 2010
BP 119
EP 128
DE Ensemble of Dichotomizers; Error-Correcting Output Codes; Evolutionary optimization
AB The classication of large number of object categories is a challenging trend in the Machine Learning eld. In literature, this is often addressed using an ensemble of classiers. In this scope, the Error-Correcting Output Codes framework has demonstrated to be a powerful tool for the combination of classiers. However, most of the state-of-the-art ECOC approaches use a linear or exponential number of classiers, making the discrimination of a large number of classes unfeasible. In this paper, we explore and propose a minimal design of ECOC in terms of the number of classiers. Evolutionary computation is used for tuning the parameters of the classiers and looking for the best Minimal ECOC code conguration. The results over several public UCI data sets and a challenging multi-class Computer Vision problem show that the proposed methodology obtains comparable and even better results than state-of-the-art ECOC methodologies with far less number of dichotomizers.
ER