A real-time learning algorithm for a multilayered neural network based on the extended Kalman filter
- 1 April 1992
- journal article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Signal Processing
- Vol. 40 (4) , 959-966
- https://doi.org/10.1109/78.127966
Abstract
A novel real-time learning algorithm for a multilayered neural network is derived from the extended Kalman filter (EKF). Since this EKF-based learning algorithm approximately gives the minimum variance estimate of the linkweights, the convergence performance is improved in comparison with the backwards error propagation algorithm using the steepest descent techniques. Furthermore, tuning parameters which crucially govern the convergence properties are not included, which makes its application easier. Simulation results for the XOR and parity problems are provided.<>Keywords
This publication has 6 references indexed in Scilit:
- Training feed-forward networks with the extended Kalman algorithmPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2003
- Generic constraints on underspecified target trajectoriesPublished by Institute of Electrical and Electronics Engineers (IEEE) ,1989
- Experiments on neural net recognition of spoken and written textIEEE Transactions on Acoustics, Speech, and Signal Processing, 1988
- Systolic implementation on Kalman filtersIEEE Transactions on Acoustics, Speech, and Signal Processing, 1988
- Parallel Distributed ProcessingPublished by MIT Press ,1986
- Asymptotic behavior of the extended Kalman filter as a parameter estimator for linear systemsIEEE Transactions on Automatic Control, 1979