Journal article
A defeasible reasoning model of inductive concept learning from examples and communication
Artificial intelligence, v 193
01 Dec 2012
Abstract
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
Details
- Title
- A defeasible reasoning model of inductive concept learning from examples and communication
- Creators
- Santiago Ontanon - Artificial Intelligence Research InstitutePilar Dellunde - Research Institute for Artificial IntelligenceLluis Godo - Research Institute for Artificial IntelligenceEnric Plaza - Research Institute for Artificial Intelligence
- Publication Details
- Artificial intelligence, v 193
- Publisher
- Elsevier
- Number of pages
- 20
- Grant note
- FFI2008-03126-E/FILO / project LoMoReVI 2009-SGR-1433; 2009-SGR-1434 / Generalitat de Catalunya; General Electric TIN2009-14704-C03-03 / project ARINF TIN2009-13692-C03-01 / project Next-CBR
- Resource Type
- Journal article
- Language
- English
- Academic Unit
- Computer Science
- Web of Science ID
- WOS:000311977500005
- Scopus ID
- 2-s2.0-84866507808
- Other Identifier
- 991019167876004721
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