Institut Jean Nicod

Accueil > Séminaires/Colloques > Prix Jean Nicod > Récipiendaires du Prix Jean-Nicod depuis 1993 > G. HARMAN (2005) > Prix et Conférences Jean Nicod (2005)



Prix et Conférences Jean Nicod (2005)



GILBERT HARMAN

Le Problème de l’Induction et la Théorie Statistique de l’Apprentissage.
 

Notice biographique

Après des études à Swarthmore College et à l’Université de Harvard, toute la carrière du Professeur Gilbert Harman s’est déroulée à l’Université de Princeton où il enseigne la philosophie.
Gilbert Harman est l’auteur de très nombreuses contributions en épistémologie, métaphysique, éthique, philosophie du langage et de l’esprit.
Ses travaux sur le raisonnement et sur les fondements de l’éthique ont eu un retentissement condidérable.
Condidérant qu’il y a une continuité entre la philosophie et les sciences, il collabore régulièrement avec des chercheurs d’autres disciplines sur des sujets tels que la psychologie et la philosophie de la rationalité, la sémantique, l’épistémologie et la théorie de l’apprentissage ainsi que les interactions hommes-machines.
En 2002, Gilbert Harman a été élu Membre de la Cognitive Science Society.


Brochure
 

The Problem of Induction and Statistical Learning Theory

 

Monday May, 30th, 4 - 6 pm
Ecole Normale Supérieure, 45, rue d’Ulm, 75005 Paris
(Salle Dussane)
The Problem of Induction

In
assessing the reliability of inductive inferences, it is important not to think of induction and deduction as two kinds of inference, because a mistake to think that there is such a thing as deductive inference. The fact that inductive reasoning often leads one to give up things previously believed may seem to make it hard to specify what reliability comes to, but in fact developments in statistical learning theory allow a way to specify a kind of enumerative induction and answer certain questions about its reliability and about the reliability of certain other inductive methods.
[Full Text]

Gilbert Harman will be awarded the Jean-Nicod Prize after the lecture.
 

Tuesday May, 31th, 2:30 - 4:30 pm
Ecole Normale Supérieure, 45, rue d’Ulm, 75005 Paris (Salle des Actes)Enumerative Induction in Statistical Learning Theory and Popper on Falsifiability

A certain sort of enumerative induction which selects from a limited set of rules that rule that best fits the data. In the theory of machine learning, there is a precise statement of the conditions under which reliable enumerative induction of this sort is possible, namely, it is possible only if the set of hypotheses being considered is not too rich, where richness is inversely correlated with falsifiability in something like Popper’s sense. In this lecture I describe some of the relevant theory and begin to discuss Popper’s view.

Thursday June, 2nd, 2:30 - 4:30 pm
Ecole des Hautes Etudes en Sciences Sociales, 105, boulevard Raspail, 75006 Paris. (Amphitheater)
Going Beyond Enumerative Induction

A different kind of induction balances data-coverage against something like simplicity. One criterion might be the the length of a statement of the hypothesis. Another idea would be to allow infinite classes of equally simple hypotheses, so that all linear hypotheses go into one class, for example, and the complexity of a class of hypotheses is measured by the number of parameters needed to specify a particular instance of the class. Such a measure gives bad results for trigonometric functions, however, and it is necessary instead to appeal again to falsifiability, this time to measure complexity.

Friday June, 3rd, 2:30 - 4:30 pm
Ecole Normale Supérieure, 45, rue d’Ulm, 75005 Paris. (Salle des Actes)
Support Vectors and Transduction

Recent developments include use of support vector machines and methods of induction that infer directly from data to the classification of new cases as they have come up, without basing the classification on the prior acceptance of a general rule. Developments in statistical learning theory raise questions about realism versus instrumentalism, about basic science versus applied science, that is, about when to try to find an underlying rule and when to forget that and try to reach conclusions directly about the next instance.



Bibliography

Published lectures :

Gilbert Harman and Sanjeev Kulkarni. Reliable Reasoning. Induction and Statistical Learning Theory, PIT Press, 2007.
 

 2000. EXPLAINING VALUE AND OTHER ESSAYS IN MORAL PHILOSOPHY. OXFORD : CLARENDON PRESS.
1999. REASONING, MEANING, AND MIND. OXFORD : CLARENDON PRESS.
1996. MORAL RELATIVISM AND MORAL OBJECTIVITY (EN COLLAB. AVEC J. THOMSON). OXFORD : BLACKWELL.
(ED.) 1993. CONCEPTIONS OF THE HUMAN MIND : ESSAYS IN HONOR OF GEORGE A. MILLER. HILLSIDE, NJ : LAWRENCE ERLBAUM.
1990. SKEPTICISM AND THE DEFINITION OF KNOWLEDGE. NEW YORK : GARLAND.
1986. CHANGE IN VIEW : PRINCIPLES OF REASONING. CAMBRIDGE, MASSACHUSETTS : M.I.T. PRESS/BRADFORD BOOKS.
1973. THOUGHT. PRINCETON, NEW JERSEY : PRINCETON UNIVERSITY PRESS.


 

 

Centre National de la Recherche Scientifique
(Département des sciences de l’homme et de la société)

Ecole des Hautes Etudes en Sciences Sociales
Ecole Normale Supérieure

 

 


CNRS EHESS ENS ENS