Abstract
Neural networks are intended to be used in future nanoelectronics since these architectures seem to be robust against malfunctioning elements and noise. In this paper we analyze the robustness of radial basis function networks and determine upper bounds on the mean square error under noise contaminated weights and inputs.
This work was supported by the Graduate College 776 – Automatic Configuration in Open Systems- funded by the Deutsche Forschungsgemeinschaft.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
Similar content being viewed by others
References
Geva, S., Sitte, J.: A constructive method for multivariate function approximation by multilayer perceptrons. IEEE Transactions on Neural Networks 3, 621–624 (1992)
Haykin, S.: Neural Networks. A Comprehensive Foundation, 2nd edn. Prentice Hall, New Jersey (1999)
Rückert, U., Surmann, H.: Tolerance of a binary associative memory towards stuck-at-faults. In: Kohonen, T. (ed.) Artificial Neural Networks, Amsterdam, North-Holland, vol. 2, pp. 1195–1198 (1991)
Rückert, U., Kreuzer, I., Tryba, V.: Fault-tolerance of associative memories based on neural networks. In: Proceedings of the International Conference on Computer Technology, Systems and Applications, Hamburg, Germany, pp. 1.52–1.55 (1989)
Beiu, V., Rückert, U., Roy, S., Nyathi, J.: On nanoelectronic architectural challenges and solutions. In: Fourth IEEE Conference on Nanotechnology (2004)
Razavi, B.: Design of Analog CMOS Integrated Circuits. McGraw-Hill, New York (2000)
Sitte, J., Körner, T., Rückert, U.: Local cluster neural net: Analog vlsi design. Neurocomputing 19, 185–197 (1998)
Körner, T., Rückert, U., Geva, S., Malmstrom, K., Sitte, J.: Vlsi friendly neural network with localied transfer functions. In: Proceedings of the IEEE International Conference on Neural Networks, Perth, Australia, vol. 1, pp. 169–174 (1995)
Widrow, B., Kollár, J.: Quantization Noise. Prentice Hall PTR, New Jersey (2002)
Chandra, P., Singh, Y.: Feedforward sigmoidal networks - equicontinuiy and fault-tolerance properties. IEEE Transactions on Neural Networks 15, 1350–1366 (2004)
Girosi, F., Poggio, T.: Networks and the best approximation property. Biological Cybernetics 63, 169–176 (1990)
Girosi, F., Jones, M., Poggio, T.: Regularization theory and neural networks architectures. Neural Computation 7, 219–269 (1995)
Simmons, G.F.: Topology and Modern Analysis, McGray-Hill, Tokyo, Japan (1964)
Shannon, C.E.: A mathematical theory of communication. Bell System Technical Journal 27, 379–423, 623–656 (1948)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2005 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Eickhoff, R., Rückert, U. (2005). Robustness of Radial Basis Functions. In: Cabestany, J., Prieto, A., Sandoval, F. (eds) Computational Intelligence and Bioinspired Systems. IWANN 2005. Lecture Notes in Computer Science, vol 3512. Springer, Berlin, Heidelberg. https://doi.org/10.1007/11494669_33
Download citation
DOI: https://doi.org/10.1007/11494669_33
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-26208-4
Online ISBN: 978-3-540-32106-4
eBook Packages: Computer ScienceComputer Science (R0)