Prediction Error Adjusted Gaussian Process for Nonlinear Non-parametric System Identification

Er-Wei Bai

doi:10.3182/20120711-3-BE-2027.00191

Back

Prediction Error Adjusted Gaussian Process for Nonlinear Non-parametric System Identification

Journal article

Peer reviewed

Prediction Error Adjusted Gaussian Process for Nonlinear Non-parametric System Identification

Er-Wei Bai

IFAC Proceedings Volumes, Vol.45(16), pp.101-106

07/2012

DOI: 10.3182/20120711-3-BE-2027.00191

View Online

Abstract

A variant of Gaussian Process is proposed in this study for nonlinear non-parametric system identification. Only local data is used to construct the estimate. Moreover, the hyperparameters are adjusted to minimize the local weighted prediction errors. The proposed scheme seems to have semi-global modeling properties of Gaussian Process for limited data sets and also possess local convergence properties if the data set is sufficient rich.

convergence

Gaussian process

kernel

nonlinear system identification

Details

Title: Subtitle: Prediction Error Adjusted Gaussian Process for Nonlinear Non-parametric System Identification
Creators: Er-Wei Bai - Queen's University Belfast
Resource Type: Journal article
Publication Details: IFAC Proceedings Volumes, Vol.45(16), pp.101-106
DOI: 10.3182/20120711-3-BE-2027.00191
ISSN: 1474-6670
Language: English
Date published: 07/2012
Academic Unit: Electrical and Computer Engineering
Record Identifier: 9984197230702771

Metrics

16 Record Views