期刊
NEUROCOMPUTING
卷 70, 期 13-15, 页码 2460-2466出版社
ELSEVIER
DOI: 10.1016/j.neucom.2006.09.004
关键词
identification; neural networks; Kalman filter; stability
Compared to normal learning algorithms, for example backpropagation, Kalman filter-based algorithm has some better properties, such as faster convergence, although this algorithm is more complex and sensitive to the nature of noises. In this paper, extended Kalman filter is applied to train state-space recurrent neural networks for nonlinear system identification. In order to improve robustness of Kalman filter algorithm dead-zone robust modification is applied to Kalman filter. Lyapunov method is used to prove that the Kalman filter training is stable. (C) 2006 Elsevier B.V. All rights reserved.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据