Title :
A new method for evaluating the log-likelihood gradient (score) of linear dynamic systems
Author :
Segal, Mordechai ; Weinstein, Ehud
Author_Institution :
Dept. of Electron. Syst., Tel-Aviv Univ., Israel
fDate :
8/1/1988 12:00:00 AM
Abstract :
A novel method is presented that is based on the optimal smoothing equations. The result can be used for efficient calculations and approximations of gradient-search algorithms for maximum-likelihood estimation of the unknown system parameters. The method is applied to the continuous-discrete case
Keywords :
discrete time systems; linear systems; optimisation; parameter estimation; stochastic systems; discrete time systems; dynamic systems; gradient-search algorithms; linear systems; log-likelihood gradient; maximum-likelihood estimation; optimal smoothing equations; optimisation; parameter estimation; stochastic systems; Covariance matrix; Differential equations; Filtering; Kalman filters; Maximum likelihood estimation; Riccati equations; Signal processing algorithms; Smoothing methods; Stochastic systems; Systems engineering and theory;
Journal_Title :
Automatic Control, IEEE Transactions on
