Skip to main content
SpringerLink
Log in

Fast learning with incremental RBF networks

  • Published:
Neural Processing Letters Aims and scope Submit manuscript

Abstract

We present a new algorithm for the construction of radial basis function (RBF) networks. The method uses accumulated error information to determine where to insert new units. The diameter of the localized units is chosen based on the mutual distances of the units. To have the distance information always available, it is held up-to-date by a Hebbian learning rule adapted from the “Neural Gas≓ algorithm. The new method has several advantages over existing methods and is able to generate small, well-generalizing networks with comparably few sweeps through the training data.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Log in via an institution

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Similar content being viewed by others

References

  1. T.M Martinetz, K. J. Schulten. A “neural-gas≓ network learns topologies, in:Artificial Neural Networks, T. Kohonen, K. Mäkisara, O. Simula, J. Kangas eds., North-Holland, Amsterdam, pp. 397–402, 1991.

    Google Scholar 

  2. J. Moody, C. Darken. Learning with localized receptive fields,Proc. 1988 Connectionist Models Summer School, D. Touretzky, G. Hinton, T. Sejnowski eds., Morgan Kaufmann, San Mateo, pp. 133–143, 1989.

    Google Scholar 

  3. J.C. Platt. A resource-allocating network for function interpolation,Neural Computation, vol. 3, pp. 213–225, 1991.

    MathSciNet  Google Scholar 

  4. B. Fritzke. Supervised learning with growing cell structures, in:Advances in Neural Information Processing Systems 6, J. Cowan, G. Tesauro, J. Alspector eds., Morgan Kaufmann Publishers, San Mateo, CA, pp. 255–262, 1994.

    Google Scholar 

  5. T. Kohonen. Self-organized formation of topologically correct feature maps,Biological Cybernetics, vol. 43, pp. 59–69, 1982.

    Article  MATH  MathSciNet  Google Scholar 

  6. T. Martinetz. Competitive Hebbian learning rule forms perfectly topology preserving maps,Proc. ICANN'93: International Conference on Artificial Neural Networks (Amsterdam), 1993.

Download references

Author information

Authors and Affiliations

  1. Institut für Neuroinformatik, Ruhr-Universität Bochum, D-44780, Bochum, Germany

    Bernd Fritzke

Authors
  1. Bernd Fritzke
    View author publications

    You can also search for this author in PubMed Google Scholar

Rights and permissions

Reprints and permissions

About this article

Cite this article

Fritzke, B. Fast learning with incremental RBF networks. Neural Process Lett 1, 2–5 (1994). https://doi.org/10.1007/BF02312392

Download citation

  • Issue Date:

  • DOI: https://doi.org/10.1007/BF02312392

Keywords

Search

Navigation