Weight Parameter Optimization by the Ho--Kashyap Algorithm in MRF Models for Supervised Image Classification.

Autor: Serpico, Sebastiano B.¹, Moser, Gabriele¹

Publikováno v: IEEE Transactions on Geoscience & Remote Sensing. Dec2006, Vol. 44 Issue 12, p3695-3705. 11p.

Tento výsledek nelze pro nepřihlášené uživatele zobrazit.
K zobrazení výsledku je třeba se přihlásit.

Tento výsledek nelze pro nepřihlášené uživatele zobrazit.
K zobrazení výsledku je třeba se přihlásit.

Ho-Kashyap Classifier with Early Stopping for Regularization

Autor: Fabien Lauer, Gérard Bloch

Publikováno v: Pattern Recognition Letters
Pattern Recognition Letters, Elsevier, 2006, 27 (9), pp.1037-1044. ⟨10.1016/j.patrec.2005.12.009⟩

17 pages; International audience; This paper focuses on linear classification using a fast and simple algorithm known as the Ho-Kashyap learning rule (HK). In order to avoid overfitting and instead of adding a regularization parameter in the criterio

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::53d81765bcfd60b0c2ac9d4fa7c3252d
https://hal.archives-ouvertes.fr/hal-00021551

Ho–Kashyap with Early Stopping Versus Soft Margin SVM for Linear Classifiers –An Application

Autor: Patrice Aknin, Mohamed Bentoumi, Gérard Bloch, Fabien Lauer, Gilles Millérioux

Publikováno v: Advances in Neural Networks – ISNN 2004 ISBN: 9783540228417
ISNN (1)
Lecture Notes in Computer Science, Volume 3173, Advances in Neural Networks – ISNN 2004
International Symposium on Neural Networks
International Symposium on Neural Networks, Aug 2004, Dalian, China. pp.524-530, ⟨10.1007/b99834⟩

6 pages; International audience; In a classification problem, hard margin SVMs tend to minimize the generalization error by maximizing the margin. Regularization is obtained with soft margin SVMs which improve performances by relaxing the constraints

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::4c3f0e2f742559beb6d315549728f445
https://doi.org/10.1007/978-3-540-28647-9_87