Date: 03 Jun 2005

A note on learning DNF formulas using equivalence and incomplete membership queries

* Final gross prices may vary according to local VAT.

Get Access

Abstract

In this note, we prove with derandomization techniques that a subclass of DNF formulas with nonconstant number of terms is polynomial time learnable using equivalence and incomplete membership queries. Although many concept classes are known to be polynomial time learnable using equivalence and membership queries, so far only two concept classes are known to be polynomial time learnable (see, [AS] and [GM]) when incomplete membership queries are used.

The author was supported by by NSF grant CCR91-9103055 and by a Boston University Presidential Graduate Fellowship