Exact learning via the Monotone theory

Authors:
N. H. Bshouty
Affiliations:
Dept. of Comput. Sci., Calgary Univ., Alta., Canada
Venue:
SFCS '93 Proceedings of the 1993 IEEE 34th Annual Foundations of Computer Science
Year:
1993

Citing 0
Cited 6

The query complexity of finding local minima in the lattice

Information and Computation
Translating between Horn representations and their characteristic models

Journal of Artificial Intelligence Research
Default-reasoning with models

IJCAI'95 Proceedings of the 14th international joint conference on Artificial intelligence - Volume 1
Learning to reason the non monotonic case

IJCAI'95 Proceedings of the 14th international joint conference on Artificial intelligence - Volume 2
Boosting theory towards practice: recent developments in decision tree induction and the weak learning framework

AAAI'96 Proceedings of the thirteenth national conference on Artificial intelligence - Volume 2
Minimum multiple characterization of biological data using partially defined boolean formulas

Proceedings of the 27th Annual ACM Symposium on Applied Computing

Quantified Score

Hi-index	0.01

Visualization

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.