Learning Fallible Deterministic Finite Automata

Abstract

We consider the problem of learning from a fallible expert that answers all queries about a concept, but often gives incorrect answers. The expert can also be thought of as a truth table describing the concept which has been partially corrupted. In order to learn the underlying concept with arbitrarily high precision, we would like to use its structure in order to correct most of the incorrect answers. We assume that the expert's errors are uniformly and independently distributed, occur with any fixed probability strictly smaller than 1/2, and are persistent. In particular, we present a polynomial time algorithm using membership queries for correcting and learning fallible Deterministic Finite Automata under the uniform distribution.