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.
This work was partially supported by Grant Agency of the Czech Republic under grants number 201/93/0427, 201/94/0729 and 201/95/0976.
This is a preview of subscription content, log in via an institution.
Buying options
Tax calculation will be finalised at checkout
Purchases are for personal use only
Learn about institutional subscriptionsPreview
Unable to display preview. Download preview PDF.
References
Albertini, F., Sontag, E.D.: For neural networks, function determines form, Neural Networks, 6, 975–990, (1993).
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.
Chen, A.M., Haw-minn, L., Hecht-Nielsen, R.: On the geometry of feedforward neural network error surfaces, Neural Computation, 5, 910–927, (1993).
Goldberg D.E.: Genetic algorithms in search, optimization, and machine learning. New York: Addison- Wesley, 1989.
Hecht-Nielsen, R.: On the algebraic structure of feedforward network weight spaces. In Advanced Neural Computers, 129–135, Elsevier, 1990.
Hlaváčková, K., Neruda, R.: Radial Basis Function Networks, Neural Network World, 3, 1, 93–101 (1993).
Kainen, P. et al: A New Criterion for Choosing an Activation Function: Uniqueness Leads to Faster Learning, Neural Parallel and Scientific Computations (in press)
Kůrková, V., Kainen, P.: Functionally Equivalent Feedforward Networks, Neural Computation, 6, 543–558, (1993).
Kůrková, V., Neruda, R. Uniqueness of Functional Representation by Gaussian Basis Function Networks. In Proceedings of ICANN′94, 417–474, Springer: London, 1994.
Sussmann, H.J.: Uniqueness of the weights for minimal feedforward nets with a given input-output map, Neural Networks, 5, 4, 589–594, (1992).
Author information
Authors and Affiliations
Rights and permissions
Copyright information
© 1995 Springer-Verlag/Wien
About this paper
Cite this paper
Neruda, R. (1995). Functional Equivalence and Genetic Learning of RBF Networks. In: Artificial Neural Nets and Genetic Algorithms. Springer, Vienna. https://doi.org/10.1007/978-3-7091-7535-4_16
Download citation
DOI: https://doi.org/10.1007/978-3-7091-7535-4_16
Publisher Name: Springer, Vienna
Print ISBN: 978-3-211-82692-8
Online ISBN: 978-3-7091-7535-4
eBook Packages: Springer Book Archive