An algorithm based on the Extended Kalman Filter (EKF) for optimization of parameters in neural networks is presented and a convergence analysis of the estimated parameters values to the optimal ones is made. By using results on stochastic stability of EKF in filtering for discrete-time nonlinear systems, it is proved that the approximation error of the proposed learning method is locally exponentially bounded in mean square. Such a training can be performed also in batch mode and outperforms well-known training methods, as shown by means of simulation results.
On the convergence EKF-based parameters optimization for neural networks
ALESSANDRI, ANGELO;SANGUINETI, MARCELLO
2003-01-01
Abstract
An algorithm based on the Extended Kalman Filter (EKF) for optimization of parameters in neural networks is presented and a convergence analysis of the estimated parameters values to the optimal ones is made. By using results on stochastic stability of EKF in filtering for discrete-time nonlinear systems, it is proved that the approximation error of the proposed learning method is locally exponentially bounded in mean square. Such a training can be performed also in batch mode and outperforms well-known training methods, as shown by means of simulation results.File in questo prodotto:
Non ci sono file associati a questo prodotto.
I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.