A case based comparison of identification with neural network and Gaussian process models.

Juš Kocijan, Blaž Banko, Bojan Likar, Agathe Girard, Roderick Murray‐Smith, Carl Edward RasmussenMPG.PuRe 2003

Abstract

In this paper an alternative approach to black-box identification of non-linear dynamic systems is compared with the more established approach of using artificial neural networks. The Gaussian process prior approach is a representative of non-parametric modelling approaches. It was compared on a pH process modelling case study. The purpose of modelling was to use the model for control design. The comparison revealed that even though Gaussian process models can be effectively used for modelling dynamic systems caution has to be axercised when signals are selected.
BibTeX
@inproceedings{kocijan2003case,
  author = {Juš Kocijan and Blaž Banko and Bojan Likar and Agathe Girard and Roderick Murray‐Smith and Carl Edward Rasmussen},
  title = {{A case based comparison of identification with neural network and Gaussian process models.}},
  booktitle = {MPG.PuRe},
  year = {2003},
}

Loading related content...

Figure