Title :
Recurrent neural network training by nprKF joint estimation
Author :
Feldkamp, Lee A. ; Feldkamp, Timothy M. ; Prokhorov, Danil V.
Author_Institution :
Res Lab., Ford Motor Co., Dearborn, MI, USA
fDate :
6/24/1905 12:00:00 AM
Abstract :
We present a method for training recurrent networks with the joint estimation of states and parameters, using the "derivative-free" formulation for nonlinear Kalman filters by Norgaard, Poulsen, and Ravn (2000). Our approach is consistent with that described by Williams (1992) for the extended Kalman filter (EKF). We extend the treatment to handle multistream training and propose ways of making the required computation more efficient
Keywords :
Kalman filters; learning (artificial intelligence); parameter estimation; recurrent neural nets; state estimation; Norgaard-Poulsen-Ravn approach; learning; multistream training; nonlinear Kalman filters; parameter estimation; recurrent neural network; state estimation; Backpropagation; Computer networks; Covariance matrix; Kalman filters; Neural networks; Parameter estimation; Recurrent neural networks; Recursive estimation; Stability; State estimation;
Conference_Titel :
Neural Networks, 2002. IJCNN '02. Proceedings of the 2002 International Joint Conference on
Conference_Location :
Honolulu, HI
Print_ISBN :
0-7803-7278-6
DOI :
10.1109/IJCNN.2002.1007463
