Abstract
Using smooth membership functions and activation functions presumably enhances the performance of neural, fuzzy and neuro-fuzzy systems. In this work we present some results based on the efficient generation of gaussian piecewise-linear approximations and its application to neural/fuzzy parallel computing systems. The application of approximations to the gaussian nodes of radial basis function networks (RBFN), and the observation of the approximation capabilities of the networks after applying various learning algorithms, is revealing. We use the equivalence theorem between RBFN’s and certain fuzzy inference systems for extracting conclusions applicable to de fuzzy world.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
References
Basterretxea K., Tarela J.M, and del Campo I. (1999) PWL Approximation of Non-Linear Functions for the Implementation of Neuro-Fuzzy Systems, In: Proceedings of the CSCC’99 3rd World Multiconference on Circuits, Systems, Communications and Computers, Athens, Greece, pp. 3001 - 3007.
Castro J. L. (1996) Fuzzy Logic Controllers Are Universal Approximators”, IEEE Transactions on Systems, Man and Cybernetics, vol. 25, no. 4, pp. 629 - 635.
Chen C. L., Chen W. C. and Chang F.-Y. (1993) Hybrid Learning Algorithm for Gaussian Potential Function Networks”, IEEE Proceedings-D, vol. 140, no. 6, pp. 442 - 448.
Esposito A., Marinaro M., Oricchio D. and Scarpetta S. (2000) Approximation of Continuous Mappings by a Growing Neural RBF-based Algorithm”, Neural Networks, vol. 13, pp. 651 - 665.
Jang, J. S. R. and Sun, C. T. (1993) Functional Equivalence Between Radial Basis Function Networks and Fuzzy Inference Systems. IEEE Trans. on Neural Networks, vol., no. 1, pp..
Lee S. and Rhee M. K. (1991) A Gaussian Potential Function Network with Hierarchically Self-Organizing Learning, Neural Networks, vol. 4, pp. 207 - 224.
Takagi T., and Sugeno M. (1985), Fuzzy Identification of Systems and its Application to Modelling and Contro, IEEE Transactions on Systems Man and Cybernetics, vol. 15, pp. 116 - 132.
Tarela J.M., Basterretxea K., del Campo I., Martínez M.V., and Alonso E. (2002) Optimised PWL Recursive Approximation and its Application to Neuro-Fuzzy Systems, Mathematical and Computer Modelling, vol. 35, no. 7-8, pp. 867 - 883.
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2004 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Basterretxea, K., Tarela, J.M., del Campo, I. (2004). Gaussian Function Approximation in Neuro-Fuzzy Systems. In: Lotfi, A., Garibaldi, J.M. (eds) Applications and Science in Soft Computing. Advances in Soft Computing, vol 24. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-540-45240-9_23
Download citation
DOI: https://doi.org/10.1007/978-3-540-45240-9_23
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-40856-7
Online ISBN: 978-3-540-45240-9
eBook Packages: Springer Book Archive