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.
Similar content being viewed by others
References
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.
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.
J.C. Platt. A resource-allocating network for function interpolation,Neural Computation, vol. 3, pp. 213–225, 1991.
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.
T. Kohonen. Self-organized formation of topologically correct feature maps,Biological Cybernetics, vol. 43, pp. 59–69, 1982.
T. Martinetz. Competitive Hebbian learning rule forms perfectly topology preserving maps,Proc. ICANN'93: International Conference on Artificial Neural Networks (Amsterdam), 1993.
Author information
Authors and Affiliations
Rights 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
Issue Date:
DOI: https://doi.org/10.1007/BF02312392