Ensemble methods try to combine multiple models to obtain a better prediction performance. These methods, developed over the last 20 years, can make a more stable and more precise prediction and they are highly competitive with any other method. However, there are several approaches to the construction of ensemble methods and research in this field is far from over. In this paper we compare some approaches for supervised classification.
Ensemble Learning for Classification / DI CIACCIO, Agostino; Giorgi, Giovanni Maria. - ELETTRONICO. - 1:(2015). (Intervento presentato al convegno 52 Riunione Scientifica SIEDS tenutosi a Ancona nel 28-30 maggio 2015).
Ensemble Learning for Classification
DI CIACCIO, AGOSTINO;GIORGI, Giovanni Maria
2015
Abstract
Ensemble methods try to combine multiple models to obtain a better prediction performance. These methods, developed over the last 20 years, can make a more stable and more precise prediction and they are highly competitive with any other method. However, there are several approaches to the construction of ensemble methods and research in this field is far from over. In this paper we compare some approaches for supervised classification.I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.
