Training RBF network to tolerate single node fault

Kevin Ho, Chi-sing Leung, John Sum

Research output: Journal Publications and ReviewsRGC 21 - Publication in refereed journalpeer-review

5 Citations (Scopus)

Abstract

In this paper, an objective function for training a radial basis function (RBF) network to handle single node open fault is presented. Based on the definition of this objective function, we propose a training method in which the computational complexity is the same as that of the least mean squares (LMS) method. Simulation results indicate that our method could greatly improve the fault tolerance of RBF networks, as compared with the one trained by LMS method. Moreover, even if the tuning parameter is misspecified, the performance deviation is not significant. © 2011 Elsevier B.V.
Original languageEnglish
Pages (from-to)1046-1052
JournalNeurocomputing
Volume74
Issue number6
DOIs
Publication statusPublished - 15 Feb 2011

Research Keywords

  • Fault tolerant neural networks
  • RBF
  • Single node fault

Fingerprint

Dive into the research topics of 'Training RBF network to tolerate single node fault'. Together they form a unique fingerprint.

Cite this