Parameterized normalization : application to wavelet networks

Richard Baron 1 Bernard Girau 2
2 CORTEX - Neuromimetic intelligence
INRIA Lorraine, LORIA - Laboratoire Lorrain de Recherche en Informatique et ses Applications
Abstract : 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.
Type de document :
Communication dans un congrès
IJCNN, 1998, none, 5 p, 1998
Liste complète des métadonnées
Contributeur : Publications Loria <>
Soumis le : jeudi 19 octobre 2006 - 15:40:17
Dernière modification le : mercredi 21 mars 2018 - 18:57:10


  • HAL Id : inria-00108033, version 1



Richard Baron, Bernard Girau. Parameterized normalization : application to wavelet networks. IJCNN, 1998, none, 5 p, 1998. 〈inria-00108033〉



Consultations de la notice