DocumentCode
2891817
Title
Exact learning of read-twice DNF formulas
Author
Aizenstein, Howard ; Pitt, L.
Author_Institution
Dept. of Comput. Sci., Illinois Univ., Urbana, IL, USA
fYear
1991
fDate
1-4 Oct 1991
Firstpage
170
Lastpage
179
Abstract
A polynomial-time algorithm is presented for exactly learning the class of read-twice DNF formulas, i.e. Boolean formulas in disjunctive normal form where each variable appears at most twice. The (standard) protocol used allows the learning algorithm to query whether a given assignment of Boolean variables satisfies the DNF formula to be learned (membership queries), as well as to obtain counterexamples to the correctness of its current hypothesis which can be any arbitrary DNF formula (equivalence queries). The formula output by the learning algorithm is logically equivalent to the formula to be learned
Keywords
Boolean functions; computational complexity; learning systems; Boolean formulas; disjunctive normal form; equivalence queries; exact learning; membership queries; polynomial-time algorithm; protocol; read-twice DNF formulas; Computer science; Educational institutions; Inference algorithms; Polynomials; Prediction algorithms; Predictive models; Probability distribution; Protocols; Public key cryptography; Telephony;
fLanguage
English
Publisher
ieee
Conference_Titel
Foundations of Computer Science, 1991. Proceedings., 32nd Annual Symposium on
Conference_Location
San Juan
Print_ISBN
0-8186-2445-0
Type
conf
DOI
10.1109/SFCS.1991.185366
Filename
185366
Link To Document