NEURAL NET BASED NONSTANDARD A/D CONVERSION

被引：5

作者：

ANASTASSIOU, D ^{[1
]}

机构：

[1] COLUMBIA UNIV,CTR TELECOMMUN RES,NEW YORK,NY 10027

来源：

ELECTRONICS LETTERS | 1988年 / 24卷 / 10期

关键词：

CODES; SYMBOLIC - PULSE CODE MODULATION - SYSTEMS SCIENCE AND CYBERNETICS - Neural Nets;

D O I：

10.1049/el:19880419

中图分类号：

TM [电工技术]; TN [电子技术、通信技术];

学科分类号：

0808 ; 0809 ;

摘要：

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.

引用

页码：619 / 620

页数：2

共 6 条

[1] IMAGE-PROCESSING BY SIMULATED ANNEALING [J].