Stochastic approximation algorithms and applications
Stochastic approximation algorithms and applications
复制标题
DOI：
10.1109/cdc.1973.269114
复制
发表时间：
1973-12
期刊：
影响因子：
--
通讯作者：
C. Kubrusly;J. Gravier
中科院分区：
文献类型：
--
作者：
C. Kubrusly;J. Gravier
本研究提出了随机逼近算法的适用条件，最小化的均方误差标准识别的线性离散时间静止系统没有动态分子。讨论了收敛的加速问题。然后提出了一种尝试性的方法来克服先前的状态可达性要求。
This study presents the conditions of applicability of stochastic approximation algorithms that minimize a mean-square error criterion for identification of a linear discrete-time stationary system without dynamical numerator. The acceleration of the convergence is discussed. Then a tentative is outlined to overcome the previous requirement of states accessibility.