Fault Tolerance for faults in Artificial Neural Networks: Robust Fault Tolerance for Multinode faults in RBF Neural Networks - Softcover

V, Saritha

 
9786200324030: Fault Tolerance for faults in Artificial Neural Networks: Robust Fault Tolerance for Multinode faults in RBF Neural Networks
Softcover
ISBN 10: 6200324034 ISBN 13: 9786200324030
Verlag: LAP LAMBERT Academic Publishing, 2019

Inhaltsangabe

This bookk addresses the fault tolerance of RBF networks where all hidden nodes have the same fault rate and their fault probabilities are independent. Assuming that there is a Gaussian distributed noise in the output data, we have derived an objective function for robustly training an RBF network based on the Kullback–Leibler divergence. We also find that for a fault-tolerance regularizer some eigenvalues of the regularization matrix should be negative. For the Tipping’s regularizer and the OLS regularizer, the regularization matrices are positive or semipositive definite. Hence, they cannot efficiently handle the multinode open fault.

Die Inhaltsangabe kann sich auf eine andere Ausgabe dieses Titels beziehen.

Reseña del editor

This bookk addresses the fault tolerance of RBF networks where all hidden nodes have the same fault rate and their fault probabilities are independent. Assuming that there is a Gaussian distributed noise in the output data, we have derived an objective function for robustly training an RBF network based on the Kullback–Leibler divergence. We also find that for a fault-tolerance regularizer some eigenvalues of the regularization matrix should be negative. For the Tipping’s regularizer and the OLS regularizer, the regularization matrices are positive or semipositive definite. Hence, they cannot efficiently handle the multinode open fault.

„Über diesen Titel“ kann sich auf eine andere Ausgabe dieses Titels beziehen.

Verlag
LAP LAMBERT Academic Publishing
Erscheinungsdatum
2019
Sprache
Englisch
ISBN 10 
6200324034
ISBN 13 
9786200324030
Einband
Tapa blanda
Anzahl der Seiten
64
Kontakt zum Hersteller
Nicht verfügbar
Verantwortliche Person
Nicht verfügbar