Neuronal algorithms for full information spectral analysis - Département Métrologie Instrumentation & Information Accéder directement au contenu
Communication Dans Un Congrès Année : 1996

Neuronal algorithms for full information spectral analysis

Résumé

In Pattern Recognition the input items have to be identified under various transformations of their representations. Contemporary neural-networks research concentrates mostly on decision making systems, whereas the fundamental functions associated with the preprocessing of observations have often been ignored. This paper is a step toward theories that are expected to help the emergence of invariant-features
Fichier principal
Vignette du fichier
esarda96.pdf (975.43 Ko) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)

Dates et versions

hal-00221535 , version 1 (28-01-2008)

Identifiants

  • HAL Id : hal-00221535 , version 1

Citer

Vincent Vigneron, Alexandre Fayolle, Jean-Marc Martinez, Anne-Catherine Simon, Robert Junca, et al.. Neuronal algorithms for full information spectral analysis. 18th Annual ESARDA Symposium on Safeguards and Nuclear Material Managements, Nov 1996, Ispra, Italy. ⟨hal-00221535⟩
104 Consultations
51 Téléchargements

Partager

Gmail Facebook X LinkedIn More