Title :
Neural net based nonstandard A/D conversion
Author_Institution :
Dept. of Electr. Eng., Columbia Univ., New York, NY
fDate :
5/12/1988 12:00:00 AM
Abstract :
A technique for nonstandard A/D conversion of signals subject to a fidelity criterion is described, based on Hopfield neural networks. Switched-capacitor neural networks offer a natural means for efficient implementation of the proposed technique. Applications include all forms of PCM coding, oversampled A/D conversion and digital image halftoning
Keywords :
analogue-digital conversion; encoding; neural nets; pulse-code modulation; switched capacitor networks; Hopfield neural networks; PCM coding; digital image halftoning; fidelity criterion; nonstandard A/D conversion; oversampled A/D conversion; signal quantisation; switched capacitor neural networks;
Journal_Title :
Electronics Letters
