Human Discovery and Machine Learning - LIRMM - Laboratoire d’Informatique, de Robotique et de Microélectronique de Montpellier Access content directly
Journal Articles International Journal of Cognitive Informatics and Natural Intelligence Year : 2008

Human Discovery and Machine Learning


This paper studies machine learning paradigms from the point of view of human cognition. Indeed, conceptions in both mahine learning and human learning evolved from a passive to an active conception of learning. Our objective is to provide an interaction protocol suited to both humans and machines, to eable assisting human discoveries by learning machines. We identify the limitations of common machine learning paradigms in the context of scientific discovery, and we propose an extension inspired by game theory and multi-agent systems. We present individual cognitive aspects of this protocol as well as social considerations, and we relate encouraging results concerning a game implementing it.
Fichier principal
Vignette du fichier
IJCINI_simple.pdf (718.68 Ko) Télécharger le fichier

Dates and versions

lirmm-00274308 , version 1 (17-04-2008)



Christopher Dartnell, Eric Martin, Hélène Hagège, Jean Sallantin. Human Discovery and Machine Learning. International Journal of Cognitive Informatics and Natural Intelligence, 2008, 2 (4), pp.55-69. ⟨10.4018/jcini.2008100105⟩. ⟨lirmm-00274308⟩
282 View
1080 Download



Gmail Facebook X LinkedIn More