Exact Learning of Subclasses of CDNF Formulas with Membership Queries
نویسنده
چکیده
We consider the exact learnability of subclasses of Boolean formulas from membership queries alone. We show how to combine known learning algorithms that use membership and equivalence queries to obtain new learning results only with memberships. In particular we show the exact learnability of read-k monotone formulas, Sat-k O(log n)-CDNF, and O(p log n)-size CDNF from membership queries only.
منابع مشابه
Boolean Formulas are Hard to Learn for most Gate Bases
Boolean formulas are known not to be PAC-predictable even with membership queries under some cryptographic assumptions. In this paper, we study the learning complexity of some subclasses of boolean formulas obtained by varying the basis of elementary operations allowed as connectives. This broad family of classes includes, as a particular case, general boolean formulas, by considering the basis...
متن کاملEvaluation of DNF Formulas
We consider the Stochastic Boolean Function Evaluation (SBFE) problem for classes of DNF formulas. The SBFE problem for DNF formulas is a “sequential testing” problem where we need to determine the value of DNF formula on an initially unknown input x = (x1, ..., xn), when there is a cost ci associated with obtaining the value of xi, each xi is equal to 1 with known probability pi, and the xi ar...
متن کاملOracles and Queries That Are Sufficient for Exact Learning
We show that the class of all circuits is exactly learnable in randomized expected polynomial time using subset and superset queries. This is a consequence of the following result which we consider to be of independent interest: circuits are exactly learnable in randomized expected polynomial time with equivalence queries and the aid of an NP-oracle. We also show that circuits are exactly learn...
متن کاملA General Dimension for Exact Learning
We introduce a new combinatorial dimension that gives a good approximation of the number of queries needed to learn in the exact learning model, no matter what set of queries is used. This new dimension generalizes previous dimensions providing upper and lower bounds for all sorts of queries, and not for just example-based queries as in previous works. Our new approach gives also simpler proofs...
متن کاملNew Steps on the Exact Learning of CNF
A major problem in computational learning theory is whether the class of formulas in conjunctive normal form (CNF) is efficiently learnable. Although it is known that this class cannot be polynomially learned using either membership or equivalence queries alone, it is open whether CNF can be polynomially learned using both types of queries. One of the most important results concerning a restric...
متن کامل