Francesco Bergadano

Learning Behaviors of Automata from Multiplicity and Equivalence Queries

We consider the problem of identifying the behavior of an unknown automaton with multiplicity in the field

Inductive database relations

Ratviii

Inductive Synthesis of Logic Programs and Inductive Logic Programming

of rational numbers (

The difficulties of learning logic programs with cut

Ratviii

Probably approximately correct learning in fuzzy classification systems

-automaton) from multiplicity and equivalence queries. We provide an algorithm which is polynomial in the size of the

Test case generation by means of learning techniques

Ratviii

Funtional Inductive Logic Programming with Queries to the User

-automaton and in the maximum length of the given counterexamples. As a consequence, we have that

Learning Membership Functions

Ratviii

Learning relations and logic programs

-automata are probably approximately correctly learnable (PAC-learnable) in polynomial time when multiplicity queries are allowed. A corollary of this result is that regular languages are polynomially predictable using membership queries with respect to the representation of unambiguous nondeterministic automata. This is important since there are unambiguous automata such that the equivalent deterministic automaton has an exponentially larger number of states.

Learning Relations: Basing Top-Down Methods on Inverse Resolution

The concept of an inductive relation is introduced, as a natural development of other forms of intentional information, such as views and relations defined deductively. A class of top-down methods for computing such inductive relations is analyzed. Major problems produced by recursive and interdependent relations are considered. >