A Reconfigurable Satlin/Sigmoid/Gaussian/Triangular Basis Functions Computation Circuit

Author

Abuelma´ati, Muhammad Taher ; Shwehneh, Abdullah

Author_Institution

King Fahd Univ. of Pet. & Minerals, Dhahran

fYear

2006

fDate

4-7 Dec. 2006

Firstpage

1172

Lastpage

1175

Abstract

A CMOS Satlin/Sigmoid/Gaussian/triangular Basis functions computation circuit suitable for analog neural networks is proposed. The circuit can be configured to realize any of the four functions. The circuit can approximate these functions with relative root-mean-square error less than 1%. It is shown that the center, width, and peak amplitude of the dc transfer characteristic can be independently controlled. HSPICE simulation results using 0.18 mum CMOS process model parameters of TSMC technology are included

Keywords

CMOS digital integrated circuits; Gaussian processes; neural chips; radial basis function networks; reconfigurable architectures; 0.18 micron; CMOS computation circuit; CMOS process; Gaussian basis function; HSPICE simulation; Satlin basis function; Sigmoid basis function; TSMC technology; analog neural networks; computation circuit suitable; dc transfer characteristic; reconfigurable computation circuit; triangular basis functions; Analog computers; Artificial neural networks; CMOS analog integrated circuits; CMOS process; Circuit simulation; Computer networks; MOSFETs; Neural networks; Neurons; Very large scale integration; CMOS circuits; analog neural networks; computational circuits;

fLanguage

English

Publisher

ieee

Conference_Titel

Circuits and Systems, 2006. APCCAS 2006. IEEE Asia Pacific Conference on

Conference_Location

Singapore

Print_ISBN

1-4244-0387-1

Type

conf

DOI

10.1109/APCCAS.2006.342350

Filename

4145607