A NEURAL-NETWORK FOR ERROR-CORRECTING DECODING OF BINARY LINEAR CODES

被引：17
|
作者：
ESPOSITO, A [1 ]
RAMPONE, S [1 ]
TAGLIAFERRI, R [1 ]
机构：
[1] UNIV SALERNO,DIPARTIMENTO FIS TEOR & SMSA,I-84081 BARONISSI,ITALY
来源：
NEURAL NETWORKS | 1994年 / 7卷 / 01期
关键词：
NEURAL NETWORK; THRESHOLD TUNING; MAXIMUM LIKELIHOOD DECODING; LINEAR CODES; PARALLEL PROGRAMMING;
D O I：
10.1016/0893-6080(94)90068-X
中图分类号：
TP18 [人工智能理论];
学科分类号：
081104 ; 0812 ; 0835 ; 1405 ;
摘要：
We describe a neural net model that can be used to decode code words belonging to a binary linear code and to correct noisy patterns that it receives from a transmission channel. The net reduces the error probability to zero in the range of the error-correcting capacity of the code. We show a net simulation done in DISC, a general purpose parallel programming environment based on the CSP model.
引用
收藏
页码：195 / 202
页数：8
相关论文
共 50 条
12345