Title:
|
Decision trees have approximate fingerprints
|
Author:
|
Lavín Puente, Víctor Angel; Raghavan, Vijay
|
Other authors:
|
Universitat Politècnica de Catalunya. Departament de Ciències de la Computació |
Abstract:
|
We prove that decision trees exhibit the
"approximate fingerprint" property,
and therefore are not polynomially learnable
using only equivalence queries.
A slight modification of the proof
extends this result to several other representation classes
of boolean concepts which have been studied in
computational learning theory. |
Subject(s):
|
-Àrees temàtiques de la UPC::Informàtica::Informàtica teòrica -Decision trees -Aproximate fingerprint property -Computational learning |
Rights:
|
|
Document type:
|
Article - Published version Report |
Share:
|
|