Recurrent neural network training by nprKF joint estimation

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 exte...

Full description

Saved in:
Bibliographic Details
Published inProceedings of the 2002 International Joint Conference on Neural Networks. IJCNN'02 (Cat. No.02CH37290) Vol. 3; pp. 2086 - 2091 vol.3
Main Authors Feldkamp, L.A., Feldkamp, T.M., Prokhorov, D.V.
Format Conference Proceeding
LanguageEnglish
Published IEEE 2002
Subjects
Backpropagation
Computer networks
Covariance matrix
Kalman filters
Neural networks
Parameter estimation
Recurrent neural networks
Recursive estimation
Stability
State estimation
Online AccessGet full text

Cover

More Information
Summary: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.
ISBN:0780372786
9780780372788
ISSN:1098-7576
1558-3902
DOI:10.1109/IJCNN.2002.1007463