Martin Enqvist
Linköping University, Linköping, Sweden
E-mail: maren@isy.liu.se
Many approximation results in nonlinear system identification concern particular signal distributions. In this seminar, a number of results about approximate models of nonlinear systems for input signals such as minimum-phase filtered white noise, separable or Gaussian signals will be presented. Furthermore, a reweighting approach that can be used to generalize some of these results to arbitrary input signals will be discussed.