Towards a connectionist argumentation framework

S. D.Avila Garcez, D. M. Gabbay, L. C. Lamb

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

1 Scopus citations

Abstract

While neural networks have been successfully used in a number of machine learning applications, logical languages have been the standard for the representation of legal and argumentative reasoning [6]. In this paper, we present a new hybrid model of computation that allows for the deduction and learning of argumentative reasoning. We do so by using Neural-Symbolic Learning Systems to translate argumentation networks into standard neural networks. The approach enables cummulative argumentation through learning, as the strength of the arguments change over time.

Original languageEnglish
Title of host publicationECAI 2004 - 16th European Conference on Artificial Intelligence, including Prestigious Applications of Intelligent Systems, PAIS 2004 - Proceedings
EditorsRamon Lopez de Mantaras, Lorenza Saitta
PublisherIOS Press BV
Pages987-988
Number of pages2
ISBN (Electronic)9781586034528
StatePublished - 2004
Externally publishedYes
Event16th European Conference on Artificial Intelligence, ECAI 2004 - Valencia, Spain
Duration: 22 Aug 200427 Aug 2004

Publication series

NameFrontiers in Artificial Intelligence and Applications
Volume110
ISSN (Print)0922-6389
ISSN (Electronic)1879-8314

Conference

Conference16th European Conference on Artificial Intelligence, ECAI 2004
Country/TerritorySpain
CityValencia
Period22/08/0427/08/04

Fingerprint

Dive into the research topics of 'Towards a connectionist argumentation framework'. Together they form a unique fingerprint.

Cite this