arrow
返回

The NLMS algorithm in block floating-point format

delete2004-03-01
delete6
PRE
AI
A
Abhijit Mitra
M
Mrityunjoy Chakraborty
DOI:10.1109/LSP.2003.822891delete
delete原文链接
delete原文求助
delete分享
delete收藏
摘要

摘要

En 中文
We present a novel scheme to implement the normalized least mean square algorithm in block floating-point (BFP) format, which permits processing of data over a wide dynamic range, at a cost significantly less than that of a floating-point processor. Appropriate BFP formats for both the data and the filter coefficients are adopted. Care is taken so that the chosen formats remain invariant to interblock transition and weight-updating operation, respectively. Care is also taken to prevent overflow during filtering, as well as weight-updating processes, by using a dynamic scaling of the data and a slightly reduced range for the step size control parameter, with the latter having negligible effect on convergence speed.
Keyword:
adaptive filters
block floating-point (BFP) arithmetic
normalized least mean square (NLMS) methods
AI总结

AI总结

对已上传原文的论文进行重点信息的提取,主要内容包括:简要概述、研究摘要、背景介绍、关键亮点、图文解析、展望与总结。

期刊

IEEE Signal Processing Magazine 封面图
IEEE Signal Processing Magazine
IF:
9.6
论文数:
1.1W
被引数:
1.7W

机构

暂无机构信息
引用论文

引用论文

没有更多内容