Radial Basis Function Networks

  • Charu C. Aggarwal


Radial basis function (RBF) networks represent a fundamentally different architecture from what we have seen in the previous chapters. All the previous chapters use a feed-forward network in which the inputs are transmitted forward from layer to layer in a similar fashion in order to create the final outputs.


  1. [6]
    C. Aggarwal. Machine learning for text. Springer, 2018.Google Scholar
  2. [41]
    C. M. Bishop. Neural networks for pattern recognition. Oxford University Press, 1995.Google Scholar
  3. [43]
    C. M Bishop. Improving the generalization properties of radial basis function neural networks. Neural Computation, 3(4), pp. 579–588, 1991.Google Scholar
  4. [51]
    D. Broomhead and D. Lowe. Multivariable functional interpolation and adaptive networks. Complex Systems, 2, pp. 321–355, 1988.MathSciNetzbMATHGoogle Scholar
  5. [57]
    M. Buhmann. Radial Basis Functions: Theory and implementations. Cambridge University Press, 2003.Google Scholar
  6. [65]
    S. Chen, C. Cowan, and P. Grant. Orthogonal least-squares learning algorithm for radial basis function networks. IEEE Transactions on Neural Networks, 2(2), pp. 302–309, 1991.CrossRefGoogle Scholar
  7. [84]
    T. Cover. Geometrical and statistical properties of systems of linear inequalities with applications to pattern recognition. IEEE Transactions on Electronic Computers, pp. 326–334, 1965.Google Scholar
  8. [125]
    B. Fritzke. Fast learning with incremental RBF networks. Neural Processing Letters, 1(1), pp. 2–5, 1994.CrossRefGoogle Scholar
  9. [173]
    E. Hartman, J. Keeler, and J. Kowalski. Layered neural networks with Gaussian hidden units as universal approximations. Neural Computation, 2(2), pp. 210–215, 1990.CrossRefGoogle Scholar
  10. [182]
    S. Haykin. Neural networks and learning machines. Pearson, 2008.Google Scholar
  11. [256]
    M. Kubat. Decision trees can initialize radial-basis function networks. IEEE Transactions on Neural Networks, 9(5), pp. 813–821, 1998.MathSciNetCrossRefGoogle Scholar
  12. [323]
    C. Micchelli. Interpolation of scattered data: distance matrices and conditionally positive definite functions. Constructive Approximations, 2, pp. 11–22, 1986.MathSciNetCrossRefGoogle Scholar
  13. [342]
    J. Moody and C. Darken. Fast learning in networks of locally-tuned processing units. Neural Computation, 1(2), pp. 281–294, 1989.CrossRefGoogle Scholar
  14. [347]
    M. Musavi, W. Ahmed, K. Chan, K. Faris, and D. Hummels. On the training of radial basis function classifiers. Neural Networks, 5(4), pp. 595–603, 1992.CrossRefGoogle Scholar
  15. [363]
    M. J. L. Orr. Introduction to radial basis function networks, University of Edinburgh Technical Report, Centre of Cognitive Science, 1996.
  16. [365]
    J. Park and I. Sandberg. Universal approximation using radial-basis-function networks. Neural Computation, 3(1), pp. 246–257, 1991.CrossRefGoogle Scholar
  17. [366]
    J. Park and I. Sandberg. Approximation and radial-basis-function networks. Neural Computation, 5(2), pp. 305–316, 1993.CrossRefGoogle Scholar
  18. [423]
    H. Sarimveis, A. Alexandridis, and G. Bafas. A fast training algorithm for RBF networks based on subtractive clustering. Neurocomputing, 51, pp. 501–505, 2003.CrossRefGoogle Scholar
  19. [430]
    B. Schölkopf, K. Sung, C. Burges, F. Girosi, P. Niyogi, T. Poggio, and V. Vapnik. Comparing support vector machines with Gaussian kernels to radial basis function classifiers. IEEE Transactions on Signal Processing, 45(11), pp. 2758–2765, 1997.CrossRefGoogle Scholar
  20. [530]
    D. Wettschereck and T. Dietterich. Improving the performance of radial basis function networks by learning center locations. NIPS Conference, pp. 1133–1140, 1992.Google Scholar

Copyright information

© Springer International Publishing AG, part of Springer Nature 2018

Authors and Affiliations

  • Charu C. Aggarwal
    • 1
  1. 1.IBM T. J. Watson Research CenterInternational Business MachinesYorktown HeightsUSA

Personalised recommendations