Dynamic systems identification with Gaussian processes. (English) Zbl 1122.93081
Summary: This paper describes the identification of nonlinear dynamic systems with a Gaussian process (GP) prior model. This model is an example of the use of a probabilistic non-parametric modelling approach. GPs are flexible models capable of modelling complex nonlinear systems. Also, an attractive feature of this model is that the variance associated with the model response is readily obtained, and it can be used to highlight areas of the input space where prediction quality is poor, owing to the lack of data or complexity (high variance). We illustrate the GP modelling technique on a simulated example of a nonlinear system.
MSC:
| 93E12 | Identification in stochastic control theory |
References:
| [1] | Neal RM, Lecture Notes in Statistics 118 (1996) |
| [2] | O’Hagan A, Journal of the Royal Statistical Society B 40 pp 1– (1978) |
| [3] | Rasmussen CE 1996 Evaluation of Gaussian processes and other methods for non-linear regression PhD dissertation, Graduate Department of Computer Science, University of Toronto, Toronto, Canada |
| [4] | Murray-Smith R, Proceedings of the 5th European Control Conference (1999) |
| [5] | Leith DJ, Proceedings of the UKACC Control Conference (2000) |
| [6] | Gregorčič G, Proceedings of the Irish Signals and Systems Conference pp pp. 141–147– (2002) |
| [7] | Murray-Smith R, Proceedings of the 15th IFAC Congress pp 934– (2002) |
| [8] | Solak E, Advances in Neural Information Proceeding Systems 15 pp 529– (2003) |
| [9] | Girard A, Advances in Neural Information Proceeding Systems 15 pp 1033– (2003) |
| [10] | Kocijan J, Proceedings of the 4th International IMCAS Symposium on Mathematical Modelling (2003) |
| [11] | Kocijan J, Preprints of IFAC International Conference on Intelligent Control Systems and Signal Processing pp 137– (2003) |
| [12] | Williams CKI, Learning in Graphical Models pp 599– (1998) · doi:10.1007/978-94-011-5014-9_23 |
| [13] | Abrahamsen P, Norwegian Computer Centre (1997) |
| [14] | Murray-Smith R, Proceedings of the Irish Signals and Systems Conference pp 147– (2001) |
| [15] | Quiñonero Candela J Girard A Rasmussen CE 2002 Prediction at an uncertain input for Gaussian processes and relevance vector machines–application to time-series forecasting Technical Report 18/2003, Informatics and Mathematical Modelling, Danish Technical University |
| [16] | Williams CKI, Advances in Neural Information Processing Systems 13 pp 682– (2001) |
| [17] | Seeger M, Proceedings of the 9th International Workshop on Artificial Intelligence and Statistics (2003) |
| [18] | DOI: 10.1002/acs.744 · Zbl 1019.93001 · doi:10.1002/acs.744 |
| [19] | DOI: 10.1162/089976600300014908 · doi:10.1162/089976600300014908 |
| [20] | Murray-Smith R, Department of Computing Science, Glasgow University (2003) |
This reference list is based on information provided by the publisher or from digital mathematics libraries. Its items are heuristically matched to zbMATH identifiers and may contain data conversion errors. In some cases that data have been complemented/enhanced by data from zbMATH Open. This attempts to reflect the references listed in the original paper as accurately as possible without claiming completeness or a perfect matching.
