Probably approximately correct learning of Horn envelopes from queries

07/16/2018
by   Daniel Borchmann, et al.
0

We propose an algorithm for learning the Horn envelope of an arbitrary domain using an expert, or an oracle, capable of answering certain types of queries about this domain. Attribute exploration from formal concept analysis is a procedure that solves this problem, but the number of queries it may ask is exponential in the size of the resulting Horn formula in the worst case. We recall a well-known polynomial-time algorithm for learning Horn formulas with membership and equivalence queries and modify it to obtain a polynomial-time probably approximately correct algorithm for learning the Horn envelope of an arbitrary domain.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
01/23/2019

Adaptive Exact Learning of Decision Trees from Membership Queries

In this paper we study the adaptive learnability of decision trees of de...
research
05/18/2021

Actively Learning Concepts and Conjunctive Queries under ELr-Ontologies

We consider the problem to learn a concept or a query in the presence of...
research
05/06/2020

On the Learnability of Possibilistic Theories

We investigate learnability of possibilistic theories from entailments i...
research
05/20/2023

Learning Horn Envelopes via Queries from Large Language Models

We investigate an approach for extracting knowledge from trained neural ...
research
03/14/2020

Partial Queries for Constraint Acquisition

Learning constraint networks is known to require a number of membership ...
research
05/16/2023

Can we forget how we learned? Representing states in iterated belief revision

The three most common representations of states in iterated belief revis...
research
01/22/2019

Solving linear program with Chubanov queries and bisection moves

This short article focus on the link between linear feasibility and gene...

Please sign up or login with your details

Forgot password? Click here to reset