Comments on "A decision feedback recurrent neural equalizer as an infinite impulse response filter"

被引：1

作者：

Hacioglu, K ^{[1
]}

机构：

[1] Univ Colorado, Dept Comp Sci, Boulder, CO 80309 USA

来源：

IEEE TRANSACTIONS ON SIGNAL PROCESSING | 2000年 / 48卷 / 04期

关键词：

neural equalizers; nonlinear equalization; recurrent neural networks;

D O I：

10.1109/78.827557

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：

This correspondence corrects and clarifies some notation inconsistencies and the absence of some definitions in a previous paper by Ong et al.. In addition, we show that the assumptions made in the derivation of the MSEDFRNE-MSERNE invalidate the final result given in Ong et aland lead to an unfair comparison between the two equalizers. We present a simulation that best compares the two equalizers.

引用

页码：1206 / 1207

页数：2

共 4 条

[1]

BRADLEY MJ, 1995, P ICASSP DETR MI, V5, P3399

[2] USING RECURRENT NEURAL NETWORKS FOR ADAPTIVE COMMUNICATION CHANNEL EQUALIZATION [J].