论文信息 - A radial basis function network (RBFN) for function approximation

A radial basis function network (RBFN) for function approximation

A radial basis function network (RBFN) circuit for function approximation is presented. Simulation and experimental results show that the network has good approximation capabilities. The RBFN was a squared hyperbolic secant with three adjustable parameters-amplitude, width and center. To test the network a sinusoidal and sinc function was approximated.

N. Oki | M.B. Lucks

[1] Ching-Shiow Tseng,et al. An orthogonal neural network for function approximation , 1996, IEEE Trans. Syst. Man Cybern. Part B.

[2] Philippe Thissen,et al. A CMOS analog circuit for Gaussian functions , 1996 .

[3] Sukhan Lee,et al. A Gaussian potential function network with hierarchically self-organizing learning , 1991, Neural Networks.

[4] Luke Theogarajan,et al. A scalable low voltage analog Gaussian radial basis circuit , 1997 .

[5] C. Turchetti,et al. A general approach to nonlinear synthesis with MOS analog circuits , 1993 .

[6] Larry S. Davis,et al. Human expression recognition from motion using a radial basis function network architecture , 1996, IEEE Trans. Neural Networks.

[7] Larry S. Davis,et al. An improved radial basis function network for visual autonomous road following , 1996, IEEE Trans. Neural Networks.

[8] Sergio Franco,et al. Design with Operational Amplifiers and Analog Integrated Circuits , 1988 .

[9] Jui-Ming Chang,et al. A Gaussian synapse circuit for analog VLSI neural networks , 1994, IEEE Trans. Very Large Scale Integr. Syst..

[10] Tzi-Dar Chiueh,et al. A tunable Gaussian/square function computation circuit for analog neural networks , 1998 .