Paper Info
Title
Dead-zone Kalman filter algorithm for recurrent neural networks
Abstract
Abstract—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 robustnees 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.
Year
DOI
Venue
2005
10.1109/CDC.2005.1582548
conference on decision and control
DocType
ISSN
Citations 
Conference
0743-1546
8
PageRank 
References 
Authors
0.53
11
2
Name
Order
Citations
PageRank
José De Jesús Rubio157436.29
Wen Yu228322.70