An Integrated Framework for Learning and Reasoning

TL;DR

This paper introduces FLARE, a unified framework that integrates inductive learning with reasoning, highlighting their interdependence and demonstrating its application through various examples and systems.

Contribution

The paper proposes FLARE, a novel framework combining learning and reasoning in AI, bridging the gap between neural and symbolic approaches.

Findings

FLARE effectively integrates learning and reasoning processes.

The framework successfully handles classical induction and reasoning protocols.

Demonstrated applicability in simple expert systems.

Abstract

Learning and reasoning are both aspects of what is considered to be intelligence. Their studies within AI have been separated historically, learning being the topic of machine learning and neural networks, and reasoning falling under classical (or symbolic) AI. However, learning and reasoning are in many ways interdependent. This paper discusses the nature of some of these interdependencies and proposes a general framework called FLARE, that combines inductive learning using prior knowledge together with reasoning in a propositional setting. Several examples that test the framework are presented, including classical induction, many important reasoning protocols and two simple expert systems.