Learning a subclass of k-quasi-Horn formulas with membership queries

Authors:
Víctor Lavín Puente
Affiliations:
Dpto. Sistemas Informáticos y Computación, Universidad Complutense, E-28040 Madrid, Spain
Venue:
Information Processing Letters
Year:
2011

Citing 6
Cited 0

Negative Results for Equivalence Queries

Machine Learning
Learning Conjunctions of Horn Clauses

Machine Learning - Computational learning theory
Read-twice DNF formulas are properly learnable

Information and Computation
Learning nearly monotone k-term DNF

Information Processing Letters
Efficient Read-Restricted Monotone CNF/DNF Dualization by Learning with Membership Queries

Machine Learning
Monotone term decision lists

Theoretical Computer Science

Quantified Score

Hi-index	0.89

Visualization

Abstract

Boolean formulas have been widely studied in the field of learning theory. We focus on the model of learning with queries, and study a restriction of the class of k-quasi-Horn formulas, that is, conjunctive normal form formulas where the number of unnegated literals per clause is at most k. This class is known to be as hard to learn as the general class CNF of conjunctive normal form formulas. By imposing some constraints, we define a fragment of this logic that can be learned using only membership queries. Also we prove that none of these constraints makes by itself the class learnable.