A simple neural-based A/D converter employing CMOS inverters

Author

Pham, Cong-Kha ; Tanaka, Mamoru ; Shono, Katsufusa

Author_Institution

Dept. of Electr. & Electron. Eng., Sophia Univ., Tokyo, Japan

Volume

4

fYear

1994

fDate

27 Jun-2 Jul 1994

Firstpage

2093

Abstract

A simple neural-based A/D converter employing only CMOS inverters is considered. Its structure is based on a neural network with feedforward and nonsymmetrical connections. The formal neuron model can easily be implemented by the use of CMOS inverters. Weights for synapses are given as fixed numerical values of channel conductances of pull-up PMOS and pull-down NMOS transistors of the CMOS inverters. A 4-bit A/D converter is realized with 3 μm CMOS digital process and is measured for confirming the behavior of the proposed structure

Keywords

CMOS digital integrated circuits; analogue-digital conversion; feedforward neural nets; logic gates; neural chips; CMOS inverters; channel conductances; feedforward; formal neuron model; neural-based A/D converter; nonsymmetrical connections; pull-down NMOS transistor; pull-up PMOS transistor; synaptic weights; CMOS technology; Feedforward neural networks; Feedforward systems; Hardware; Inverters; Neural networks; Neurofeedback; Neurons; Resistors; Semiconductor device modeling;

fLanguage

English

Publisher

ieee

Conference_Titel

Neural Networks, 1994. IEEE World Congress on Computational Intelligence., 1994 IEEE International Conference on

Conference_Location

Orlando, FL

Print_ISBN

0-7803-1901-X

Type

conf

DOI

10.1109/ICNN.1994.374537

Filename

374537