Bshouty, N.H.
Dept. of Comput. Sci., Calgary Univ., Alta.;
This paper appears in: Foundations of Computer Science, 1993. Proceedings., 34th Annual Symposium on
Publication Date: 3-5 Nov 1993
On page(s): 302-311
Meeting Date: 11/03/1993 - 11/05/1993
Location: Palo Alto, CA, USA
ISBN: 0-8186-4370-6
References Cited: 27
INSPEC Accession Number: 4851333
DOI: 10.1109/SFCS.1993.366857
Posted online: 2002-08-06 18:49:13.0
Abstract
We study the learnability of concept classes from membership and
equivalence queries. We develop the Monotone theory that proves (1) Any
boolean function is learnable as decision tree. (2) Any boolean function
is either learnable as DNF or as CNF (or both). The first result solves
the open problem of the learnability of decision trees and the second
result gives more evidence that DNFs are not “very hard” to
learn
Index Terms
Available to subscribers and IEEE members.
References
Available to subscribers and IEEE members.
Citing Documents
Available to subscribers and IEEE members.
