Sensitivity analysis of radial basis function networks for fault tolerance purposes

  • Xavier Parra
  • Andreu Català
Plasticity Phenomena (Maturing, Learning & Memory)
Part of the Lecture Notes in Computer Science book series (LNCS, volume 1606)


This paper introduces the concept of sensitivity in radial basis function networks. By applying a fault methodology combined with the information provided by the sensitivity of the performance error to faulty elements, faulting selection method can be simplified. In addition, the relation established between the sensitivity and a measure of the system fault toleracne permit to determine the most critical neural elements in the sense of fault tolerance. The theoretical predictions are verified by simulation experiments on two groups of problems-classification and approximation problems. In summary, this paper presents the application of sensitivity analysis for determining the most critical neural elements in the sense of fault tolerance.


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. [1]
    Deif, A.: Sensitivity Analysis in Linear Systems. Springer-Verlag, Berlin Heidelberg New York (1986)CrossRefMATHGoogle Scholar
  2. [2]
    Murray, A.F., Edwards, P.J.: Synaptic weight noise during MLP training. Enhanced MLP performance and fault tolerance resulting from synaptic weight noise during training. In: IEEE Transactions on Neural Networks, 5(5) (1994) 792–802Google Scholar
  3. [3]
    Segee, B.E., Carter, M.J.: Comparative Fault Tolerance of Parallel Distributed Processing Networks. IEEE Transactions on Computers, 43(11) (1994) 1323–1329CrossRefGoogle Scholar
  4. [4]
    Català, A., Parra, X. Fault Tolerance Parameter Model of Radial Basis Function Networks. Proceedings of the IEEE International Conference on Neural Networks, 2 (1996) 1384–1389CrossRefGoogle Scholar
  5. [5]
    Dorf, R.C., Bishop, R.H.: Moder Control Systems. 7th edn. Addison-Wesley Publishing Company (1995)Google Scholar
  6. [6]
    Prechelt, L.: PROBEN1 Neural Network Benchmark Problems. Anonymous FTP from the in directory/pub/neuronGoogle Scholar
  7. [7]
    Prechelt, L.: PROBEN1—Set of Neural Network Benchmark Problems and Benchmarking Rules. Technical Report 21/94, Department of Informatics, University of Karlsruhe (1994)Google Scholar
  8. [8]
    Orr, M.J.L.: Regularisation in the Selection of Radial Basis Function Centres. Neural Computation, 7(3):606–623 (1995).CrossRefGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 1999

Authors and Affiliations

  • Xavier Parra
    • 1
  • Andreu Català
    • 1
  1. 1.Department of Automatic ControlTechnical University of CataloniaVilanova i la Geltrú, CataloniaSpain

Personalised recommendations