Towards a logical model of induction from examples and communication

Santiago Ontañón*, Pilar Dellunde, Lluís Godo, Enric Plaza

*Corresponding author for this work

Research output: Chapter in BookChapterResearchpeer-review

2 Citations (Scopus)

Abstract

This paper focuses on a logical model of induction, and specifically of the common machine learning task of inductive concept learning (ICL). We define an inductive derivation relation, which characterizes which hypothesis can be induced from sets of examples, and show its properties. Moreover, we will also consider the problem of communicating inductive inferences between two agents, which corresponds to the multi-agent ICL problem. Thanks to the introduced logical model of induction, we will show that this communication can be modeled using computational argumentation.

Original languageEnglish
Title of host publicationArtificial Intelligence Research and Development
PublisherIOS Press
Pages259-268
Number of pages10
ISBN (Print)9781607506423
DOIs
Publication statusPublished - 2010

Publication series

NameFrontiers in Artificial Intelligence and Applications
Volume220
ISSN (Print)0922-6389

Keywords

  • Argumentation
  • Induction
  • Logic
  • Machine Learning

Fingerprint

Dive into the research topics of 'Towards a logical model of induction from examples and communication'. Together they form a unique fingerprint.

Cite this