Parameterized normalization : application to wavelet networks - Inria - Institut national de recherche en sciences et technologies du numérique Accéder directement au contenu
Communication Dans Un Congrès Année : 1998

Parameterized normalization : application to wavelet networks

Richard Baron
Bernard Girau

Résumé

Normalization is studied in the case of wavelet networks, and we derive a dynamic interpretation of its influence, which can be extended to several neural models. We show that data normalization may be simulated and parameterized to avoid data preprocessing, so that the normalization process becomes either tunable or dynamically adaptable. The main benefit of the proposed methods is a big reduction of the time of convergence on a satisfactory classification rate.
Fichier non déposé

Dates et versions

inria-00108033 , version 1 (19-10-2006)

Identifiants

  • HAL Id : inria-00108033 , version 1

Citer

Richard Baron, Bernard Girau. Parameterized normalization : application to wavelet networks. IJCNN, 1998, none, 5 p. ⟨inria-00108033⟩
90 Consultations
0 Téléchargements

Partager

Gmail Facebook X LinkedIn More