Abstract
In this paper, the problem of system identification is formulated as a problem in statistical learning theory. It is shown that if a particular type of uniform convergence result holds, then the traditional approach of choosing the current model to minimize the error on the observed data will eventually converge to an optimal model within the specified class. More important, the reformulation of system identification as a learning theory problem leads tofinite time estimatesfor the rate at which the estimated model converges to the optimal model. As an illustration of the approach, a result is derived showing that in the case of exponentially stable systems with fading memory, the desired uniform convergence result holds, so that the learning theory approach is applicable,providede the adjustable parameters enter the system model in a linear fashion.
Keywords
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
References
P. E. Caines, “Prediction error identification methods for stationary stochastic processes,”IEEE Trans.Autom. Controlvol. AC-21, no. 4, pp. 500–505, Aug. 1976.
P. E. Caines, “Stationary linear and nonlinear system identification and predictor set completeness,”IEEE Trans.Autom. Controlvol. AC-23, no. 4, pp. 583–594, Aug. 1978.
M. C. Campi and E. Weyer, “Finite sample properties of system identification methods,”IEEE Trans. Autom. Control, vol. AC-47no. 8, pp. 1329–1334, Aug. 2002.
D. Haussier, “Decision theoretic generalizations of the PAC model for neural net and other learning applications,”Information and Computation, vol. 100 pp.78–150, 1992.
L. Ljung, “Convergence analysis of parametric identification methods,”IEEE Trans. Autom. Control vol. AC-23no. 5, pp. 770–783, Oct. 1978.
L. LjungSystem Identification: Theory for the User.Englewood Cliffs, NJ: Prentice-Hall, 1987.
L. LjungSystem Identification: Theory for the User2nd ed. Englewood Cliffs, NJ: Prentice-Hall, 1999.
V. N. Vapnik and A. Ya. Chervonenkis, “On the uniform convergence of relative frequencies to their probabilities,”Theory of Probab. Appl.vol. 16, no. 2, pp. 264–280, 1971.
V. N. Vapnik and A. Ya. Chervonenkis, “Necessary and sufficient conditions for the uniform convergence of means to their expectations,”Theory of Probab. Appl. vol.26, no. 3, pp. 532–553, 1981.
M. VidyasagarA Theory of Learning and Generalization. London, UK: Springer-Verlag, 1997.
M. Vidyasagar and R. L. Karandikar, “A learning theory approach to system identification and stochastic adaptive control,” presented atthe IFAC Workshop on Adaptation and Learning in Control and Signal ProcessingComo, ItalyAug.2001.
M. Vidyasagar and R. L. Karandikar, “System identification: A learning theory approach,” inProceedings of the 1 Oth IEEE Conference on Decision and ControlOrlando, FL, Dec. 2001, pp. 2001–2006.
M. Vidyasagar and R. L. Karandikar, “A learning theory approach to system identification and stochastic adaptive control,” inProceedings of the 15th IFAC World CongressBarcelona, Spain, July 2002.
M. Vidyasagar and H. Kimura, “Robust controllers for uncertain multivariable linear systems,”Automatica vol.22, no. 1, pp. 85–94January1986.
E. Weyer, “Finite sample properties of system identification of ARX models under mixing conditions,”Automaticavol. 36, no. 9, pp. 1291–1299, Sept. 2000.
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2003 Springer Science+Business Media New York
About this chapter
Cite this chapter
Vidyasagar, M., Karandikar, R.L. (2003). System Identification: A Learning Theory Approach. In: Hashimoto, K., Oishi, Y., Yamamoto, Y. (eds) Control and Modeling of Complex Systems. Trends in Mathematics. Birkhäuser, Boston, MA. https://doi.org/10.1007/978-1-4612-0023-9_6
Download citation
DOI: https://doi.org/10.1007/978-1-4612-0023-9_6
Publisher Name: Birkhäuser, Boston, MA
Print ISBN: 978-1-4612-6577-1
Online ISBN: 978-1-4612-0023-9
eBook Packages: Springer Book Archive