We discuss some estimates for the misclassification rate of a classification tree in terms of the size of the learning set, following some ideas introduced in [3]. We develop some mathematical ideas of [3], extending the analysis to the case with an arbitrary finite number of classes.
On the size of a classification tree / Scaringella, Angela. - 2734(2003), pp. 65-72. ((Intervento presentato al convegno Third International Conference, MLDM 2003 tenutosi a Leipzig nel 5 July 2003 through 7 July 2003. - LECTURE NOTES IN COMPUTER SCIENCE. [10.1007/3-540-45065-3_6].
On the size of a classification tree
SCARINGELLA, Angela
2003
Abstract
We discuss some estimates for the misclassification rate of a classification tree in terms of the size of the learning set, following some ideas introduced in [3]. We develop some mathematical ideas of [3], extending the analysis to the case with an arbitrary finite number of classes.File allegati a questo prodotto
Non ci sono file associati a questo prodotto.
I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.
