Title
A defeasible reasoning model of inductive concept learning from examples and communication
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.
Year
DOI
Venue
2012
10.1016/j.artint.2012.08.006
Artif. Intell.
Keywords
Field
DocType
logical characterization,inductive theory,multiagent icl,inductive process,defeasible reasoning model,icl algorithm,inductive bias,inductive concept learning,inductive generalization,consequence relation,defeasible reasoning,machine learning,concept learning,argumentation,logic
Inductive reasoning,Inductive bias,Multi-task learning,Inductive transfer,Argumentation theory,Logical data model,Defeasible reasoning,Deductive reasoning,Artificial intelligence,Mathematics,Machine learning
Journal
Volume
Issue
ISSN
193,
1
0004-3702
Citations 
PageRank 
References 
6
0.43
22
Authors
4
Name
Order
Citations
PageRank
Santiago Ontañón161978.32
Pilar Dellunde215622.63
Lluís Godo388856.28
Enric Plaza445745.38