An Improved Learning Algorithm with Tunable Kernels for Complex-Valued Radial Basis Function Neural Networks
In this paper, as an extension of real-valued orthogonal least-squares regression with tunable kernels (OLSRTK), a complex-valued OLSRTK is presented which can be used to construct a suitable sparse regression model. In order to enhance the real-valued OLSRTK, the random traversal process and method of filtering center are adopted in complex-valued OLSRTK. Then, the complex-valued OLSRTK is applied to train complex-valued radial basis function neural networks. Numerical results show that better performance can be achieved by the developed algorithm than by the original real-valued OLSRTK.
KeywordsComplex-valued radial basis function neural networks Random traversal process Repeat weighted boosting search Filtering center
Unable to display preview. Download preview PDF.
- 1.Chen, S., Grant, P.M., Mclaughlin, S., Mulgrew, B.: Complex-valued Radial Basis Function Networks. In: 3rd International Conference on Artificial Neural Networks, pp. 148–152. IET Press, London (1993)Google Scholar
- 2.Pande, A., Goel, V.: Complex-valued Neural Network in Image Recognition: A Study on the Effectiveness of Radial Basis Function. World Academy of Science, Engineering and Technology 20, 220–225 (2007)Google Scholar
- 3.Li, M.Y., He, S.B., Li, X.D.: Modeling the Nonlinear Power Amplifier with Memory Using Complex-valued Radial Basis Function Networks. In: International Conference on Microwave and Millimeter Wave Technology, pp. 100–103. IEEE Press, New York (2008)Google Scholar
- 8.Botoca, C., Budura, G.: Symbol Decision Equalizer Using a Radial Basis Functions Neural Network. In: 7th WSEAS International Conference on Neural Networks, pp. 79–84. WSEAS Press, Stevens Point (2006)Google Scholar
- 12.Ceylan, M., Yacar, H.: Blood Vessel Extraction from Retinal Images Using Complex Wavelet Transform and Complex-valued Artificial Neural Network. In: 36th International Conference on Telecommunications and Signal Processing, pp. 822–825. IEEE Press, New York (2013)Google Scholar