Projective DNF formulae and their revision

Authors:
Robert H. Sloan;Balázs Szörényi;György Turán
Affiliations:
Department of Computer Science, University of Illinois at Chicago, Chicago, IL 60607-7053, USA;Research Group on Artificial Intelligence, Hungarian Academy of Sciences and University of Szeged, Szeged 6720, Hungary;Research Group on Artificial Intelligence, Hungarian Academy of Sciences and University of Szeged, Szeged 6720, Hungary and Department of Mathematics, Statistics and Computer Science, University o ...
Venue:
Discrete Applied Mathematics
Year:
2008

Learning Nested Differences of Intersection-Closed Concept Classes

Machine Learning
Additive versus exponentiated gradient updates for linear prediction

STOC '95 Proceedings of the twenty-seventh annual ACM symposium on Theory of computing
Generalized teaching dimensions and the query complexity of learning

COLT '95 Proceedings of the eighth annual conference on Computational learning theory
How many queries are needed to learn?

Journal of the ACM (JACM)
Tracking the Best Disjunction

Machine Learning - Special issue on context sensitivity and concept drift
Projection Learning

Machine Learning
A neuroidal architecture for cognitive computation

Journal of the ACM (JACM)
Concept Formation and Knowledge Revision

Concept Formation and Knowledge Revision
Theory Revision with Queries: DNF Formulas

Machine Learning
Learning Decision Lists

Machine Learning
Learning Quickly When Irrelevant Attributes Abound: A New Linear-Threshold Algorithm

Machine Learning
On-line Algorithms in Machine Learning

Developments from a June 1996 seminar on Online algorithms: the state of the art
Tracking linear-threshold concepts with Winnow

The Journal of Machine Learning Research
Queries revisited

Theoretical Computer Science - Special issue: Algorithmic learning theory
Theory revision with queries: horn, read-once, and parity formulas

Artificial Intelligence
Learnability and Automatizability

FOCS '04 Proceedings of the 45th Annual IEEE Symposium on Foundations of Computer Science

Hi-index	0.05

Combinatorial and learnability results are proven for projective disjunctive normal forms, a class of DNF expressions introduced by Valiant.