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.
CitationLavin, V., Raghavan, V. "Decision trees have approximate fingerprints". 1996.
All rights reserved. This work is protected by the corresponding intellectual and industrial property rights. Without prejudice to any existing legal exemptions, reproduction, distribution, public communication or transformation of this work are prohibited without permission of the copyright holder. If you wish to make any use of the work not provided for in the law, please contact: firstname.lastname@example.org