In this paper we present a novel dynamic programming algorithm to synthesize an optimal decision tree from OR-decision tables,an extension of standard decision tables,which allow to choose between several alternative actions in the same rule. Experiments are reported,showing the computational time improvements over state of the art implementations of connected components labeling,using this modelling technique.
In this paper we present a novel dynamic programming algorithm to synthesize an optimal decision tree from OR-decision tables, an extension of standard decision tables, which allow to choose between several alternative actions in the same rule. Experiments are reported, showing the computational time improvements over state of the art implementations of connected components labeling, using this modelling technique.
Optimal Decision Trees Generation from OR-Decision Tables / Grana, Costantino; Montangero, Manuela; Borghesani, Daniele; Cucchiara, Rita. - STAMPA. - 6978:(2011), pp. 443-452. (Intervento presentato al convegno 16th International Conference on Image Analysis and Processing, ICIAP 2011 tenutosi a Ravenna, Italy nel Sep 14-16) [10.1007/978-3-642-24085-0_46].
Optimal Decision Trees Generation from OR-Decision Tables
GRANA, Costantino;MONTANGERO, Manuela;BORGHESANI, Daniele;CUCCHIARA, Rita
2011
Abstract
In this paper we present a novel dynamic programming algorithm to synthesize an optimal decision tree from OR-decision tables, an extension of standard decision tables, which allow to choose between several alternative actions in the same rule. Experiments are reported, showing the computational time improvements over state of the art implementations of connected components labeling, using this modelling technique.
Pubblicazioni consigliate
I metadati presenti in IRIS UNIMORE sono rilasciati con licenza Creative Commons CC0 1.0 Universal, mentre i file delle pubblicazioni sono rilasciati con licenza Attribuzione 4.0 Internazionale (CC BY 4.0), salvo diversa indicazione.
In caso di violazione di copyright, contattare Supporto Iris
