Article details

Title: A Comparative Study Related to the RBF Neural Network Training
Author(s): Grigore Jeler   Stelian Spînu            

Abstract: Generally, the training process of an RBF neural network is related, as performance level, to the specific way of obtaining the mapping of RBF centers over the input data space, and the fitting method of the neural weights to the output layer, respectively. Having as starting point a concrete pattern recognition task belonging to the high-resolution radar imagery, this paper aims at presenting a comparative study of some standard and improved methods for obtaining a high-performance training process of RBF neural networks.

Keywords: neural networks, RBF neural network, pattern recognition.


[1] I.C. VIZITIU – Neuro-Fuzzy-Genetic Architectures: Theory and Applications, Military Technical Academy Publishing House, Bucharest, Romania, 2011 (in Romanian)
[2] L. JAIN, A.M. FANELLI – Recent Advances in Artificial Neural Networks: Design and Applications, CRC Press, Boca Raton, FL, 2000
[3] M.M. GUPTA, L. JIN, N. HOMMA – Static and Dynamic Neural Networks: From Fundamentals to Advanced Theory, John Wiley & Sons, Hoboken, NJ, 2003
[4] D.S. BROOMHEAD, D. LOWE – Multivariable Functional Interpolation and Adaptive Networks, Complex Systems, Vol. 2, No. 3, pp. 321-355, 1988
[5] Y.H. HU, J.-N. HWANG (Eds.) – Handbook of Neural Network Signal Processing, CRC Press, Boca Raton, FL, 2002
[6] B.D. RIPLEY – Pattern Recognition and Neural Networks, Cambridge University Press, Cambridge, UK, 2002
[7] N.B. KARAYIANNIS, M.M. RANDOLPH-GIPS – On the Construction and Training of Reformulated Radial Basis Function Neural Networks, IEEE Transactions on Neural Networks, Vol. 14, No. 4, pp. 835-846, Jul. 2003
[8] R.J. HOWLETT, L.C. JAIN – Radial Basis Function Networks 2: New Advances in Design, Physica-Verlag, Heidelberg, Germany, 2001
[9] I.C. VIZITIU – Advanced ATR System Using Improved Neural Recognition and Decision Fusion Techniques, Proc. of the International Conference on Military Technologies, ICMT 2013, pp. 47-52, Brno, The Czech Republic, May 22-23, 2013
[10] H. DEMUTH, M. BEALE – Neural Network Toolbox: For Use with MATLAB, User’s Guide, Version 4, The MathWorks, Natick, MA, 2000