Advertisement

Functional Equivalence and Genetic Learning of RBF Networks

  • Roman Neruda

Abstract

In this paper a functional equivalence property of feedforward networks is introduced and studied for the case of radial basis function networks with Gaussian activation function and metrics induced by an inner product. The description of functional equivalent parameterizations is used for proposition of new genetic learning rules that operate only on a small part of the whole weight space.

Keywords

Crossover Operator Weight Space Radial Basis Function Network Hide Unit Feedforward Network 
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    Albertini, F., Sontag, E.D.: For neural networks, function determines form, Neural Networks, 6, 975–990, (1993). CrossRefGoogle Scholar
  2. 2.
    Chen, A.M., Hecht-Nielsen, R.: On the geometry of feedforward neural network weight spaces. In Proceedings of the 2nd IEE Conerence on Artificial Neural Networks 1–4, London: IEE Press, 1991.Google Scholar
  3. 3.
    Chen, A.M., Haw-minn, L., Hecht-Nielsen, R.: On the geometry of feedforward neural network error surfaces, Neural Computation, 5, 910–927, (1993).CrossRefGoogle Scholar
  4. 4.
    Goldberg D.E.: Genetic algorithms in search, optimization, and machine learning. New York: Addison- Wesley, 1989.MATHGoogle Scholar
  5. 5.
    Hecht-Nielsen, R.: On the algebraic structure of feedforward network weight spaces. In Advanced Neural Computers, 129–135, Elsevier, 1990.Google Scholar
  6. 6.
    Hlaváčková, K., Neruda, R.: Radial Basis Function Networks, Neural Network World, 3, 1, 93–101 (1993).Google Scholar
  7. 7.
    Kainen, P. et al: A New Criterion for Choosing an Activation Function: Uniqueness Leads to Faster Learning, Neural Parallel and Scientific Computations (in press)Google Scholar
  8. 8.
    Kůrková, V., Kainen, P.: Functionally Equivalent Feedforward Networks, Neural Computation, 6, 543–558, (1993).CrossRefGoogle Scholar
  9. 9.
    Kůrková, V., Neruda, R. Uniqueness of Functional Representation by Gaussian Basis Function Networks. In Proceedings of ICANN′94, 417–474, Springer: London, 1994.Google Scholar
  10. 10.
    Sussmann, H.J.: Uniqueness of the weights for minimal feedforward nets with a given input-output map, Neural Networks, 5, 4, 589–594, (1992).CrossRefGoogle Scholar

Copyright information

© Springer-Verlag/Wien 1995

Authors and Affiliations

  • Roman Neruda
    • 1
  1. 1.Institute of Computer ScienceCzech Academy of SciencesPrague 8Czech Republic

Personalised recommendations