Sy. Lin et al., A TUNABLE GAUSSIAN SQUARE FUNCTION COMPUTATION CIRCUIT FOR ANALOG NEURAL NETWORKS/, IEEE transactions on circuits and systems. 2, Analog and digital signal processing, 45(3), 1998, pp. 441-446
A Gaussian/square function computation circuit suitable for analog neu
ral networks is proposed. It can realize Gaussian and square functions
when operating in weak and strong inversion region, respectively. It
is shown that the center, width, and peak amplitude of the dc transfer
curve can be controlled separably. Measurement results on 3-mu m CMOS
fabricated chips confirm theoretical and simulation findings.