|
|||||
|
|
| 基于LS的梯度迭代最陡下降算法GISDA | |
| 引用本文： | 靳天玉,吕振肃. 基于LS的梯度迭代最陡下降算法GISDA[J]. 甘肃科学学报, 2005, 17(4): 60-62 |
| 作者姓名： | 靳天玉 吕振肃 |
| 作者单位： | 兰州大学,信息科学与工程学院,甘肃,兰州,730000 |
| 基金项目： | 甘肃省自然科学基金资助（ZS011-A25-016-G） |
| 摘 要： | 提出了一种基于LS准则、利用梯度迭代的最陡下降算法GISDA（Gradient Iteration Steepest Descent Algorithm，GISDA）．该算法在梯度计算上比LMS精确．新算法与传统的最陡下降算法相比，具有运算量小、容易实现等优点．GISDA算法比LMS算法收敛速度快、稳定性更好．并给出了GISDA算法和LMS算法性能比较的计算机仿真结果和结论． |
| 关 键 词： | 梯度迭代 自适应滤波 最陡下降算法 遗忘因子 |
| 文章编号： | 1004-0366（2005）04-0060-03 |
| 收稿时间： | 2004-12-04 |
| 修稿时间： | 2004-12-04 |
Steepest-Descending Algorithm Based on Gradient Iteration Under the LS Criterion |
|
| JIN Tian-yu,LU Zhen-su. Steepest-Descending Algorithm Based on Gradient Iteration Under the LS Criterion[J]. Journal of Gansu Sciences, 2005, 17(4): 60-62 | |
| Authors: | JIN Tian-yu LU Zhen-su |
| Affiliation: | School of lnformational Science and Engineering, Lanzhou University, Lanzhou 730000, China |
| Abstract: | A new steepest-descending algorithm based on gradient iteration is proposed under the LS criterion. The new algorithm is more accurate than LMS in computation of the gradient. It is of lower complexity in computation and far more easy to be implemented as compared with the original steepest descent algorithm. It has rapid convergence and algorithm stability. Simulation is given at the end. |
| Keywords: | gradient iteration adaptive filtering steepest descent algorithm forgetting factor |
| 本文献已被 维普 万方数据 等数据库收录！ | |