Adaptive decision making systems
Given a population of classifiers, we consider the problem of designing highly compact and error adaptive decision making systems. A selection approach based on misclassification diversity and potential cooperation among classifiers is proposed. The compactness constraint allows us the efficient imp...
Guardado en:
| Autores principales: | , , |
|---|---|
| Formato: | Objeto de conferencia |
| Lenguaje: | Inglés |
| Publicado: |
2005
|
| Materias: | |
| Acceso en línea: | http://sedici.unlp.edu.ar/handle/10915/22982 |
| Aporte de: |
| Sumario: | Given a population of classifiers, we consider the problem of designing highly compact and error adaptive decision making systems. A selection approach based on misclassification diversity and potential cooperation among classifiers is proposed. The compactness constraint allows us the efficient implementation of fuzzy integral combination rules regarding both the interpretability of fuzzy measures and low complexity of fuzzy integral operator. Experimental results show the feasibility of our approach. |
|---|