Loading...
conference paper
NARX Models: Optimal Parametric Approximation of Nonparametric Estimators
Ferrari-Trecate, G.
•
De Nicolao, G.
2001
Proceedings of the 2001 American Control Conference
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 $O(N^3)$ where $N$ 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 $O(N^2)$ focusing on their use in the parametric identification of NARX models.
Type
conference paper
Authors
Ferrari-Trecate, G.
•
De Nicolao, G.
Publication date
2001
Published in
Proceedings of the 2001 American Control Conference
Volume
6
Start page
4868
End page
4873
Peer reviewed
REVIEWED
EPFL units
Event name | Event place | Event date |
Arlington, Virginia, USA | 25-27 June | |
Available on Infoscience
January 10, 2017
Use this identifier to reference this record