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

We consider exact learning monotone CNF formulas in which each variable appears at most some constant k times ("read-k" monotone CNF). Let f : {0,1}^sup n^ [arrow right] {0,1} be expressible as a read-k monotone CNF formula for some natural number k. We give an incremental output polynomia...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:Machine learning Jg. 37; H. 1; S. 89 - 110
Hauptverfasser: Domingo, Carlos, Mishra, Nina, Pitt, Leonard
Format: Journal Article
Sprache:Englisch
Veröffentlicht: Dordrecht Springer Nature B.V 01.10.1999
Schlagworte:
ISSN:0885-6125, 1573-0565
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Beschreibung
Zusammenfassung:We consider exact learning monotone CNF formulas in which each variable appears at most some constant k times ("read-k" monotone CNF). Let f : {0,1}^sup n^ [arrow right] {0,1} be expressible as a read-k monotone CNF formula for some natural number k. We give an incremental output polynomial time algorithm for exact learning both the read-k CNF and (not necessarily read restricted) DNF descriptions of f. The algorithm's only method of obtaining information about f is through membership queries, i.e., by inquiring about the value f(x) for points x {0,1}^sup n^. The algorithm yields an incremental polynomial output time solution to the (read-k) monotone CNF/DNF dualization problem. The unrestricted versions remain open problems of importance.[PUBLICATION ABSTRACT]
Bibliographie:SourceType-Scholarly Journals-1
ObjectType-Feature-1
content type line 14
ObjectType-Article-2
content type line 23
ISSN:0885-6125
1573-0565
DOI:10.1023/A:1007627028578