A New Algorithm to Automate Inductive Learning of Default Theories

TL;DR

This paper introduces new algorithms for automatically learning default theories using non-monotonic logic programs, improving upon traditional inductive logic programming methods and aligning with human common-sense reasoning.

Contribution

The paper presents novel algorithms for inductively learning default theories in non-monotonic logic, enhancing efficiency and interpretability over existing methods.

Findings

Algorithms outperform traditional inductive logic programming approaches

Learned default theories are more comprehensible to humans

Experimental results demonstrate significant improvements

Abstract

In inductive learning of a broad concept, an algorithm should be able to distinguish concept examples from exceptions and noisy data. An approach through recursively finding patterns in exceptions turns out to correspond to the problem of learning default theories. Default logic is what humans employ in common-sense reasoning. Therefore, learned default theories are better understood by humans. In this paper, we present new algorithms to learn default theories in the form of non-monotonic logic programs. Experiments reported in this paper show that our algorithms are a significant improvement over traditional approaches based on inductive logic programming.