Zobrazeno 1 - 10
of 72
pro vyhledávání: '"Guermeur, P."'
Publikováno v:
AAAI 2023
We study inductive matrix completion (matrix completion with side information) under an i.i.d. subgaussian noise assumption at a low noise regime, with uniform sampling of the entries. We obtain for the first time generalization bounds with the follo
Externí odkaz:
http://arxiv.org/abs/2212.08339
One of the main open problems in the theory of multi-category margin classification is the form of the optimal dependency of a guaranteed risk on the number C of categories, the sample size m and the margin parameter gamma. From a practical point of
Externí odkaz:
http://arxiv.org/abs/1812.00584
Autor:
Guermeur, Yann
This article deals with the generalization performance of margin multi-category classifiers, when minimal learnability hypotheses are made. In that context, the derivation of a guaranteed risk is based on the handling of capacity measures belonging t
Externí odkaz:
http://arxiv.org/abs/1809.07310
Autor:
Guermeur, Yann
In the framework of agnostic learning, one of the main open problems of the theory of multi-category pattern classification is the characterization of the way the complexity varies with the number C of categories. More precisely, if the classifier is
Externí odkaz:
http://arxiv.org/abs/1609.07953
Autor:
Monfrini, Emmanuel, Guermeur, Yann
Using a support vector machine requires to set two types of hyperparameters: the soft margin parameter C and the parameters of the kernel. To perform this model selection task, the method of choice is cross-validation. Its leave-one-out variant is kn
Externí odkaz:
http://arxiv.org/abs/0804.4898
Autor:
Guermeur, Yann
Publikováno v:
ASMDA 2007 (2007) 1-8
Bounds on the risk play a crucial role in statistical learning theory. They usually involve as capacity measure of the model studied the VC dimension or one of its extensions. In classification, such "VC dimensions" exist for models taking values in
Externí odkaz:
http://arxiv.org/abs/0706.3679
Akademický článek
Tento výsledek nelze pro nepřihlášené uživatele zobrazit.
K zobrazení výsledku je třeba se přihlásit.
K zobrazení výsledku je třeba se přihlásit.
Autor:
Françoise Gourmelon, Michel Etienne, Mathias Rouan, Christian Kerbiriou, Marie Charles, Frédéric Bioret, Frédérique Chlous-Ducharme, Yvon Guermeur, Harold Levrel
Publikováno v:
Cybergeo (2008)
This study deals with the pluridisciplinar approach to designing an environmental model of a part of the Mer d’Iroise Biosphere Reserve (Brittany, France). A multi-agent system (MAS) is implemented. Different scenarios simulate future plausible sit
Externí odkaz:
https://doaj.org/article/759354a32be44e1c8da7fff716bb3353
Akademický článek
Tento výsledek nelze pro nepřihlášené uživatele zobrazit.
K zobrazení výsledku je třeba se přihlásit.
K zobrazení výsledku je třeba se přihlásit.
Autor:
Guermeur, Ivan
Publikováno v:
Orientalistische Literaturzeitung; July 2022, Vol. 117 Issue: 2 p103-106, 4p