TY - GEN
T1 - Recurrent neural networks training with optimal bounded ellipsoid algorithm
AU - De Rubio, José Jesús
AU - Yu, Wen
PY - 2007
Y1 - 2007
N2 - Compared to normal learning algorithms, for example backpropagation, the optimal bounded ellipsoid (OBE) algorithm has some better properties, such as faster convergence, since it has a similar structure as Kalman filter. OBE has some advantages over Kalman filter training, the noise is not required to be Guassian. In this paper OBE algorithm is applied traing the weights of recurrent neural networks for nonlinear system identification. Both hidden layers and output layers can be updated. From a dynamic systems point of view, such training can be useful for all neural network applications requiring real-time updating of the weights. A simple simulation gives the effectiveness of the suggested algorithm.
AB - Compared to normal learning algorithms, for example backpropagation, the optimal bounded ellipsoid (OBE) algorithm has some better properties, such as faster convergence, since it has a similar structure as Kalman filter. OBE has some advantages over Kalman filter training, the noise is not required to be Guassian. In this paper OBE algorithm is applied traing the weights of recurrent neural networks for nonlinear system identification. Both hidden layers and output layers can be updated. From a dynamic systems point of view, such training can be useful for all neural network applications requiring real-time updating of the weights. A simple simulation gives the effectiveness of the suggested algorithm.
UR - http://www.scopus.com/inward/record.url?scp=46449120122&partnerID=8YFLogxK
U2 - 10.1109/ACC.2007.4282818
DO - 10.1109/ACC.2007.4282818
M3 - Contribución a la conferencia
AN - SCOPUS:46449120122
SN - 1424409888
SN - 9781424409884
T3 - Proceedings of the American Control Conference
SP - 4768
EP - 4773
BT - Proceedings of the 2007 American Control Conference, ACC
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 2007 American Control Conference, ACC
Y2 - 9 July 2007 through 13 July 2007
ER -