Identification of reliable predictor models for unknown systems: A data-consistency approach based on learning theory

IFAC Proceedings Volumes (IFAC-PapersOnline)

Volumn 15, Issue 1, 2002, Pages 85-90

  Calafiore, Giuseppe ^a   Campi, M C ^b   El Ghaoui, Laurent ^c  

^a POLITECNICO DI TORINO   (Italy)

^b UNIVERSITY OF BRESCIA   (Italy)

^c UNIVERSITY OF CALIFORNIA   (United States)

Author keywords

Convex optimization; Identification; Set valued maps; VC theory

Indexed keywords

AUTOMATION; IDENTIFICATION (CONTROL SYSTEMS);

ACCURATE PREDICTION; CONSISTENCY CRITERIA; DATA CONSISTENCY; DESCRIPTOR MODELS; IDENTIFICATION PROCEDURE; SET-VALUED MAP; STATISTICAL LEARNING THEORY; VC THEORY;

CONVEX OPTIMIZATION;

EID: 84945578634     PISSN: 14746670     EISSN: None     Source Type: Conference Proceeding    
DOI: 10.3182/20020721-6-es-1901.01000     Document Type: Conference Paper

References (14)

1. Aubin, J.P. (1990). Set-valued analysis. Birkhäuser. Boston, MA.
2. Aubin, J.P. and A. Cellina (1984). Differential inclusions: set valued maps and viability theory. Springer-Verlag. New York.
3. Box, G.E.P., G.M. Jenkins and G.C. Reinsel (1994). Time series analysis: forecasting and control. Prentice Hall. Englewood Cliffs, N.J.
4. Campi, M.C. and P.R. Kumar (1998). Learning dynamical systems in a stationary environment. Sys. Control Letters 34, 125-132.
5. El Ghaoui, L. and G. Calafiore (2000). Recursive identification of models with time-varying, structured uncertainty. In: IFAC SYSID Conference. Santa Barbara, California.
6. Karpinsky, M. and A.J. Macintyre (1997). Polynomial bounds for VC dimension of sigmoidal general pfaffian neural networks. Journal of Computer System and Science 54, 169-176.
7. Ljung, L. (1999). System identification: theory for the user. Prentice Hall. Englewood Cliffs, N.J.
8. Nobel, A. and A. Dembo (1993). A note on uniform laws of averages for dependent processes. Stat. and Prob. Lett. 17, 169-172.
9. Sontag, E. (2000). VC dimension of neural networks. Available on-line at the www.address.citeseer.nj.nec.com/191558.html.
10. Vandenberghe, L. and S. Boyd (1996). Semidefinite programming. SIAM Rev. 38(1), 49-95.
11. Vapnik, V.N. and A.Y. Chervonenkis (1971). On the uniform convergence of relative frequencies to their probabilities. Theory of Probability and its Applications 16(2), 264-280.
12. Vidyasagar, M. (1997). A Theory of Learning and Generalization. Springer-Verlag. London.
13. Weyer, E. (2000). Finite sample properties of system identification of arx models under mixing conditions. Automatica 36, 1291-1299.
14. Yu, B. (1994). Rates of convergence for empirical processes of stationary mixing sequences. Annals of Probability 22(1), 94-116.