Title
From the spherical to an elliptic form of the dynamic RBF neural network influence field
Date Issued
01 January 2002
Access level
metadata only access
Resource Type
conference paper
Author(s)
Laboratoire d'Automatique de Besancon
Abstract
We introduce a new neural network architecture corresponding to the dynamic RBF with an elliptic influence field. The dynamic aspect is obtained with a self-connection, and the elliptic influence field form, by adding a supplementary RBF layer. The modified RBF neural network gives good results in monitoring applications.
Start page
107
End page
112
Volume
1
Language
English
OCDE Knowledge area
Ciencias de la computación
Ingeniería de sistemas y comunicaciones
Scopus EID
2-s2.0-0036079672
Conference
Proceedings of the International Joint Conference on Neural Networks: 2002 International Joint Conference on Neural Networks (IJCNN '02)
Sources of information:
Directorio de Producción Científica
Scopus