Skip to Main content Skip to Navigation
Journal articles

Human Discovery and Machine Learning

Abstract : 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.
Complete list of metadata

Cited literature [33 references]  Display  Hide  Download
Contributor : Christopher Dartnell <>
Submitted on : Thursday, April 17, 2008 - 6:10:30 PM
Last modification on : Thursday, June 10, 2021 - 5:08:59 PM
Long-term archiving on: : Thursday, May 20, 2010 - 11:27:10 PM



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



Record views


Files downloads