From the spherical to an elliptic form of the dynamic RBF neural network influence field

From the spherical to an elliptic form of the dynamic RBF neural network influence field

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 m...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Zemouri, R., Racoceanu, D., Zerhouni, N.
Format: Tagungsbericht
Sprache:eng
Schlagworte:
Artificial intelligence
Computer Science
Condition monitoring
Cost function
Interpolation
Machine Learning
Modems
Neural networks
Production systems
Prototypes
Radial basis function networks
Shape
Online-Zugang:Volltext bestellen
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Beschreibung
Zusammenfassung: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.
ISSN:1098-7576
1558-3902
DOI:10.1109/IJCNN.2002.1005452