Derivative observations in Gaussian process models of dynamic systems

E. Solak; R. Murray-Smith; W.E. Leithead; C. Rasmusson; D.J. Leith

Derivative observations in Gaussian process models of dynamic systems

E. Solak, R. Murray-Smith, W.E. Leithead, C. Rasmusson, D.J. Leith

Electronic And Electrical Engineering

Research output: Contribution to conference › Paper

Abstract

Gaussian processes provide an approach to nonparametric modelling which allows a straightforward combination of function and derivative observations in an empirical model. This is of particular importance in identification of nonlinear dynamic systems from experimental data. 1) It allows us to combine derivative information, and associated uncertainty with normal function observations into the learning and inference process.

Original language	English
Number of pages	8
Publication status	Published - 2002
Event	2002 Neural Information Processing (NIPS) Meeting - Vancouver, Canada Duration: 9 Dec 2002 → 11 Dec 2002

Conference

Conference	2002 Neural Information Processing (NIPS) Meeting
Country/Territory	Canada
City	Vancouver
Period	9/12/02 → 11/12/02

Keywords

derivative observations
gaussian process models
dynamic systems

Cite this

@conference{6ad4c014d3b14c6ca96f2954c2f1fe67,

title = "Derivative observations in Gaussian process models of dynamic systems",

abstract = "Gaussian processes provide an approach to nonparametric modelling which allows a straightforward combination of function and derivative observations in an empirical model. This is of particular importance in identification of nonlinear dynamic systems from experimental data. 1) It allows us to combine derivative information, and associated uncertainty with normal function observations into the learning and inference process. ",

keywords = "derivative observations, gaussian process models, dynamic systems",

author = "E. Solak and R. Murray-Smith and W.E. Leithead and C. Rasmusson and D.J. Leith",

year = "2002",

language = "English",

note = "2002 Neural Information Processing (NIPS) Meeting ; Conference date: 09-12-2002 Through 11-12-2002",

}

TY - CONF

T1 - Derivative observations in Gaussian process models of dynamic systems

AU - Solak, E.

AU - Murray-Smith, R.

AU - Leithead, W.E.

AU - Rasmusson, C.

AU - Leith, D.J.

PY - 2002

Y1 - 2002

N2 - Gaussian processes provide an approach to nonparametric modelling which allows a straightforward combination of function and derivative observations in an empirical model. This is of particular importance in identification of nonlinear dynamic systems from experimental data. 1) It allows us to combine derivative information, and associated uncertainty with normal function observations into the learning and inference process.

AB - Gaussian processes provide an approach to nonparametric modelling which allows a straightforward combination of function and derivative observations in an empirical model. This is of particular importance in identification of nonlinear dynamic systems from experimental data. 1) It allows us to combine derivative information, and associated uncertainty with normal function observations into the learning and inference process.

KW - derivative observations

KW - gaussian process models

KW - dynamic systems

UR - http://nips.cc/Conferences/2002/

M3 - Paper

T2 - 2002 Neural Information Processing (NIPS) Meeting

Y2 - 9 December 2002 through 11 December 2002

ER -

Derivative observations in Gaussian process models of dynamic systems

Abstract

Conference

Keywords

Other files and links

Fingerprint

Cite this