|
A NEW METHOD FOR THE ANALYSIS OF HIDDEN MARKOV MODEL ESTIMATES
László Gerencsér* Gábor Molnár-Sáska**
* Computer and Automation Institute
Hungarian Academy of Sciences
13-17 Kende u., Budapest 1111, Hungary
gerencser@sztaki.hu
** Computer and Automation Institute
Hungarian Academy of Sciences
13-17 Kende u., Budapest 1111, Hungary
and
Technical University of Budapest
1-3 Egry J. u., Budapest 1111, Hungary
molnar@math.bme.hu
The estimation of Hidden Markov Models has attracted a lot of attention recently. The purpose of this paper is to lay the foundation for a new approach for the analysis of the maximum-likelihood estimation of HMM-s, using representation of HMM-s. Useful connection between the estimation theory of HMM-s and linear stochastic systems is established via the theory of L-mixing processes.
Keywords: Hidden Markov Models, stochastic systems, random transformations, Doeblin condition, L-mixing processes, maximum-likelihood estimation,
Session slot T-Fr-M03: Estimation of Stochastic Systems/Area code 3d : Stochastic Systems
 | 