Hopfield神经网络非线性纠三错码的研究  

Studies on Nonlinear TEC Codes Using Hopfield Neural Networks

作　　者：高丽丽 赵西卿[1] 刘兴平[1] 

机构地区：[1]延安大学数学系

出　　处：《延安大学学报（自然科学版）》1998年第2期1-7,共7页Journal of Yan'an University：Natural Science Edition

基　　金：国家攀登计划项目;国家自然科学基金

摘　　要：本文设计了一种高散型Ｈｏｐｆｉｅｌｄ自反馈神经网络，其权值矩阵具有较强的规律性（权值矩阵是主对线为１的的对称矩阵）。将这种网络应用于编码技术，得到了纠三错的非线性（ＴＥＣ—ＦＥＤ）码，同时对非线性码的旋转平移性进行了研究。这种网络原理简单，译码复杂性低。In this paper, a new discrete Hopfield neural network with self-feedback connection is designed, the weight matrix of which is a symmetric matrix that has regular structure. By using the new neural metwork, some three-error-correcting and four-error-detecting (TEC—FED)codes are obtained. Rotation and translation properties of the new codes are studied. The new neural network is simple in principle and has lower complexity in decoding. The code obtained has obvious regularity.

关 键 词：神经网络 TEC-FED码 编码 非线性码 纠三错码 

分 类 号：TP18[自动化与计算机技术—控制理论与控制工程]