A TUNABLE GAUSSIAN SQUARE FUNCTION COMPUTATION CIRCUIT FOR ANALOG NEURAL NETWORKS/

Authors
LIN SY HUANG RJ CHIUEH TD
Citation
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
Citations number
19
Categorie Soggetti
Engineering, Eletrical & Electronic
Journal title
IEEE transactions on circuits and systems. 2, Analog and digital signal processing → ACNP
ISSN journal
10577130
Volume
45
Issue
3
Year of publication
1998
Pages
441 - 446
Database
ISI
SICI code
1057-7130(1998)45:3<441:ATGSFC>2.0.ZU;2-V
Abstract
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.