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. In this article, 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 then use the formalization to describe a multi-agent interaction protocol, that has been inspired by these paradigms and that has been validated recently on some groups of agents. Finally, we propose extensions to this protocol.
This is a preview of subscription content, log in via an institution.
Buying options
Tax calculation will be finalised at checkout
Purchases are for personal use only
Learn about institutional subscriptionsPreview
Unable to display preview. Download preview PDF.
References
Gold, E.M.: Language identification in the limit. Information and Control 10(5), 447–474 (1967)
Angluin, D.: Queries and concept learning. Machine Learning 2, 319–342 (1988)
Valiant, L.: A theory of the learnable. Commun. ACM 27, 1134–1142 (1984)
Popper, K.R.: Conjectures and Refutations: The Growth of Scientific Knowledge. Harper and Row (1963)
Hagège, H., Dartnell, C., Sallantin, J.: Positivism against constructivism: A network game to learn epistemology. In: Discovery Science (2007)
Kolmogorov, A.N.: Grundbegriffe der Wahrscheinlichkeitrechnung (Fondements de la thorie des probabilits). Springer, Heidelberg (1930)
Chaumon, L., Mazliak, L., Yor, M.: A.n. kolmogorov, quelques aspects de l’oeuvre probabiliste (2003)
Angluin, D.: Queries revisited. Theoretical Computer Science 313, 175–194 (2004)
Dartnell, C., Sallantin, J.: Assisting scientific discovery with an adaptive problem solver. In: Discovery Science, pp. 99–112 (2005)
Neumann, J.V., Morgenstern, O.: Theory of Games and Economic Behavior. Princeton University Press, Princeton (1944)
Sallantin, J.: La découverte scientifique assistée par des agents rationnels. Revue des sciences et technologie de l’information, 15–30 (2003)
Nobrega, G.M.D., Cerri, S.: A contradiction driven approach to theory information: Conceptual issues pragmatics in human learning, potentialities. Journal of the Brazilian Computer Society 9, 37–55 (2003)
Muggleton, S., Buntine, W.: Machine invention of firstorder predicates by inverting resolution. In: Fifth International Conference on Machine Learning, pp. 339–352 (1988)
Muggleton, S.: Predicate invention and utilisation. Theoretical Artificial Intelligence, 127–130 (1994)
Banerji, R.B.: Learning theoretical terms. In: Muggleton, S. (ed.) Inductive Logic Programming, pp. 93–112 (1997)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2008 Springer Berlin Heidelberg
About this paper
Cite this paper
Dartnell, C., Martin, É., Sallantin, J. (2008). Learning from Each Other. In: Jean-Fran, JF., Berthold, M.R., Horváth, T. (eds) Discovery Science. DS 2008. Lecture Notes in Computer Science(), vol 5255. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-540-88411-8_16
Download citation
DOI: https://doi.org/10.1007/978-3-540-88411-8_16
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-88410-1
Online ISBN: 978-3-540-88411-8
eBook Packages: Computer ScienceComputer Science (R0)