EM for Nonlinear System Identification

The aim of this code is illustrate how the Expectation Maximization (EM) algorithm can be used together with a particle smoother in order to solve some problems in nonlinear system identification.

MATLAB code

Click here to download the MATLAB code.

Relevant paper

All the details explaining the use of the expectation maximization (EM) algorithm for identification of nonlinear dynamical systems are provided in the following paper,

[1] Thomas B. Schön, Adrian Wills and Brett Ninness. System Identification of Nonlinear State-Space Models. Automatica, 47(1):39-49, January 2011. [pdf] [Automatica] [BibTeX]