Learning from each other

Abstract : Since its inception, the field of machine learning has seen the advent of several learning paradigms, designed to frame the issues central to the learning activity, provide effective learning methods, and investigate the power and limitations inherent to the process of successful learning. We propose a formalization that underlies the key concepts of many such paradigms and discuss their relevance to scientific discovery, with the aim of assessing what scientists can expect from machines designed to assist them in their quest for the discovery of valid laws. We illustrate the formalization on several variations of a card game, and highlight the differences that paradigms impose on learners, as well as the assumptions they make on the nature of the learning process. We use the formalization to describe a multi-agent interaction protocol inspired by these paradigms that has been validated recently. We propose extensions to this protocol.
Type de document :
Communication dans un congrès
Discovery Science 2008, Oct 2008, budapest hungary, Springer Berlin / Heidelberg, LNCS, pp.148-159, 2008, 〈http://www.inf.uni-konstanz.de/ds2008/〉. 〈10.1007/978-3-540-88411-8_16〉
Liste complète des métadonnées

https://hal-lirmm.ccsd.cnrs.fr/lirmm-00394998
Contributeur : Jean Sallantin <>
Soumis le : samedi 13 juin 2009 - 19:27:56
Dernière modification le : jeudi 11 janvier 2018 - 06:26:23

Identifiants

Collections

Citation

Jean Sallantin, Christopher Dartnell, Eric Martin. Learning from each other. Discovery Science 2008, Oct 2008, budapest hungary, Springer Berlin / Heidelberg, LNCS, pp.148-159, 2008, 〈http://www.inf.uni-konstanz.de/ds2008/〉. 〈10.1007/978-3-540-88411-8_16〉. 〈lirmm-00394998〉

Partager

Métriques

Consultations de la notice

80