Abstract
Superposition of radial basis functions centered at given prototype patterns constitutes one of the most suitable energy forms for gradient systems that perform nearest neighbor classification with real-valued static prototypes. It has been shown in [1] that a continuous-time dynamical neural network model, employing a radial basis function and a sigmoid multi-layer perceptron sub-networks, is capable of maximizing such an energy form locally, thus performing almost perfectly nearest neighbor classification, when initiated by a distorted pattern. This paper reviews the proposed design procedure and presents the results of the intensive experimentation of the classifier on random prototypes.
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.
References
Muezzinoglu, M.K., Zurada, J.M.: RBF-based neurodynamic nearest neighbor classification in real pattern space (submitted, 2005)
Garey, M.R., Johnson, D.S.: Computers and Interactability. W.H. Freeman, New York (1979)
Hopfield, J.J.: Neural networks and physical systems with emergent collective computational abilities. Proc. National Acad. Sci. 79, 2554–2558 (1982)
Bruck, J., Goodman, J.W.: A generalized convergence theorem for neural networks. IEEE Trans. Information Theory 34, 1089–1092 (1988)
Müezzinoğlu, M.K., Güzeliş, C., Zurada, J.M.: An energy function-based design method for discrete Hopfield associative memory with attractive fixed points. IEEE Trans. Neural Networks 16, 370–378 (2005)
Sanner, R.M., Slotine, J.J.M.: Gaussian networks for direct adaptive control. IEEE Trans. Neural Networks 3, 837–863 (1992)
Billings, S.A., Fung, C.F.: Recurrent radial basis function networks for adaptive noise cancellation. Neural Networks 8, 273–290 (1995)
Poggio, T., Girosi, F.: Networks for approximation and learning. Proceedings of the IEEE 78, 1481–1497 (1990)
Park, J., Sandberg, I.W.: Universal approximation using radial-basis-function networks. Neural Computation 3, 246–257 (1991)
Karayiannis, N.B.: Reformulated radial basis neural networks trained by gradient descent. IEEE Trans. Neural Networks 10, 657–671 (1999)
Khalil, H.K.: Nonlinear Systems, 3rd edn. Prentice-Hall, Englewood Cliffs (2001)
Zurada, J.M.: Introduction to Artificial Neural Systems. West, St. Paul (1992)
Michel, A.N., Liu, D.: Qualitative Analysis and Sythesis of Recurrent Neural Networks. Marcel Dekker, New York (2002)
Shampine, L.F., Reichelt, M.W.: The MATLAB ODE Suite. SIAM Journal on Scientific Computing 18, 1–22 (1997)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2006 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Müezzinoğlu, M.K. (2006). Performance Evaluation of Recurrent RBF Network in Nearest Neighbor Classification. In: Savacı, F.A. (eds) Artificial Intelligence and Neural Networks. TAINN 2005. Lecture Notes in Computer Science(), vol 3949. Springer, Berlin, Heidelberg. https://doi.org/10.1007/11803089_7
Download citation
DOI: https://doi.org/10.1007/11803089_7
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-36713-0
Online ISBN: 978-3-540-36861-8
eBook Packages: Computer ScienceComputer Science (R0)