Parameter Optimization for Step-Adaptive Approximate Least Squares

被引：2
|
作者：
Lunglmayr, M. [1 ]
Huemer, M. [1 ]
机构：
[1] Johannes Kepler Univ Linz, Inst Signal Proc, A-4040 Linz, Austria
来源：
COMPUTER AIDED SYSTEMS THEORY - EUROCAST 2015 | 2015年 / 9520卷
关键词：
Estimation; Least squares; Approximate least squares; Implementation;
D O I：
10.1007/978-3-319-27340-2_65
中图分类号：
TP18 [人工智能理论];
学科分类号：
081104 ; 0812 ; 0835 ; 1405 ;
摘要：
We discuss possible approaches for the adaption of the step width of Step-Adaptive Approximate Least Squares. We present and compare two low complexity and practically feasible adaptation functions whose parameters have been optimized based on computer simulations. We show that by applying these approaches the performance deviation of Step-Adaptive Approximate Least Squares lies within the single percentage range compared to the optimal least squares solution.
引用
收藏
页码：521 / 528
页数：8
相关论文
共 50 条
12345