Publication
Bayesian regression, a nonparametric identification technique with several appealing features, can be applied to the identification of NARX (nonlinear ARX) models. However, its computational complexity scales as where is the data set size. In order to reduce complexity, the challenge is to obtain fixed-order parametric models capable of approximating accurately the nonparametric Bayes estimate avoiding its explicit computation. In this work we derive, optimal finite-dimensional approximations of complexity focusing on their use in the parametric identification of NARX models.
Fabio Zoccolan, Gianluigi Rozza
Jean-François Molinari, Thibault Didier Roch, Fabian Barras