Title :
A radial basis function network (RBFN) for function approximation
Author :
Lucks, M.B. ; Oki, N.
Author_Institution :
Dept. de Engenharia Eletrica, Univ. Estadual Paulista, Sao Paulo, Brazil
Abstract :
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
Keywords :
SPICE; function approximation; neural chips; radial basis function networks; Gaussian function; RBF network circuit; SPICE; adjustable parameters; bipolar transistor differential pair; function approximation; gradient descent method; simulated annealing; simulation; sinc function; sinusoidal function; squared hyperbolic secant; transconductance characteristic; Circuit noise; Circuit simulation; Circuit testing; Function approximation; MOSFETs; Neural networks; Radial basis function networks; Shape; Transconductance; Voltage;
Conference_Titel :
Circuits and Systems, 1999. 42nd Midwest Symposium on
Conference_Location :
Las Cruces, NM
Print_ISBN :
0-7803-5491-5
DOI :
10.1109/MWSCAS.1999.867828
