TY - GEN
T1 - Dead-zone Kalman filter algorithm for recurrent neural networks
AU - De Jesus Rubio, José
AU - Yu, Wen
PY - 2005
Y1 - 2005
N2 - 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.
AB - 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.
UR - http://www.scopus.com/inward/record.url?scp=33847235366&partnerID=8YFLogxK
U2 - 10.1109/CDC.2005.1582548
DO - 10.1109/CDC.2005.1582548
M3 - Contribución a la conferencia
AN - SCOPUS:33847235366
SN - 0780395689
SN - 9780780395688
T3 - Proceedings of the 44th IEEE Conference on Decision and Control, and the European Control Conference, CDC-ECC '05
SP - 2562
EP - 2567
BT - Proceedings of the 44th IEEE Conference on Decision and Control, and the European Control Conference, CDC-ECC '05
T2 - 44th IEEE Conference on Decision and Control, and the European Control Conference, CDC-ECC '05
Y2 - 12 December 2005 through 15 December 2005
ER -