Logo image
A defeasible reasoning model of inductive concept learning from examples and communication
Journal article   Open access   Peer reviewed

A defeasible reasoning model of inductive concept learning from examples and communication

Santiago Ontanon, Pilar Dellunde, Lluis Godo and Enric Plaza
Artificial intelligence, v 193
01 Dec 2012
url
https://doi.org/10.1016/j.artint.2012.08.006View
Published, Version of Record (VoR)Open Access (Publisher-Specific) Open

Abstract

Computer Science Computer Science, Artificial Intelligence Science & Technology Technology
This paper introduces a logical model of inductive generalization, and specifically of the machine learning task of inductive concept learning (ICL). We argue that some inductive processes, like ICL, can be seen as a form of defeasible reasoning. We define a consequence relation characterizing which hypotheses can be induced from given sets of examples, and study its properties, showing they correspond to a rather well-behaved non-monotonic logic. We will also show that with the addition of a preference relation on inductive theories we can characterize the inductive bias of ICL algorithms. The second part of the paper shows how this logical characterization of inductive generalization can be integrated with another form of non-monotonic reasoning (argumentation), to define a model of multiagent ICL This integration allows two or more agents to learn, in a consistent way, both from induction and from arguments used in the communication between them. We show that the inductive theories achieved by multiagent induction plus argumentation are sound, i.e. they are precisely the same as the inductive theories built by a single agent with all data. (C) 2012 Elsevier B.V. All rights reserved.

Metrics

11 Record Views
11 citations in Scopus

Details

InCites Highlights

Data related to this publication, from InCites Benchmarking & Analytics tool:

Collaboration types
Domestic collaboration
International collaboration
Web of Science research areas
Computer Science, Artificial Intelligence
Logo image