Support vector machines (SVM) are used for system identification of both linear and
nonlinear dynamic systems. Discrete time linear models are used to illustrate parameter
estimation and nonlinear models demonstrate model structure identification. The VC-
dimension of a trained SVM indicates the model accuracy without using separate validation
data. We conclude that SVM have potential in the field of dynamic system identification, but
that there are a number of significant issues to be addressed.

In this document we propose the use of a widely known learning-from-examples paradigm,
namely the Support Vector Machines for Regression (SVRs), for system identification
problems. We start off with the identification of a simple linear system taken from the
literature, and proceed with the non-linear case as a second step.