Learning-theoretic approach to model-set identification

Asian Journal of Control

Volumn 3, Issue 1, 2001, Pages 10-20

  Oishi, Yasuaki ^a   Kimura, Hidenori ^a  

^a UNIVERSITY OF TOKYO   (Japan)

Author keywords

Agnostic learning theory; Law of large numbers; Model set identification; Robust control; Sample complexity

Indexed keywords

LEARNING ALGORITHMS; NONLINEAR SYSTEMS; ROBUSTNESS (CONTROL SYSTEMS); UNCERTAIN SYSTEMS;

AGNOSTIC LEARNING THEORY; MODEL-SET IDENTIFICATION; SAMPLE COMPLEXITY;

IDENTIFICATION (CONTROL SYSTEMS);

EID: 0035264013     PISSN: 15618625     EISSN: None     Source Type: Journal    
DOI: 10.1111/j.1934-6093.2001.tb00037.x     Document Type: Article

References (26)

1. The complexity of model classes, and smoothing noisy data
2. Learning dynamical systems in a stationary environment
3. Quantification of uncertainty in transfer function estimation: A mixed probabilistic-worst-case approach
4. Quantifying the error in estimated transfer functions with application to model order selection
5. Decision theoretic generalizations of the PAC model for neural net and other learning applications
6. ∞
7. Probability inequalities for sums of bounded random variables
8. On convergence proofs in system identification - a general principle using ideas from learning theory
9. Optimal estimation theory for dynamic systems with set membership uncertainty: An overview
10. Properties of the empirical characteristic function and its application to testing for independence
11. Learning-theoretic system identification for robust control
12. Application of a learning theory to set-membership identification
13. A set-based approach for white noise modeling
14. A time-domain approach to model validation
15. On a class of Rank order tests for independence in multivariate distributions
16. Optimal asymptotic identification under bounded disturbances
17. A theory of the learnable
18. Identification in the presence of classes of unmodeled dynamics and noise
19. Finite sample properties of linear model identification
20. Structure of model uncertainty for a weakly corrupted plant
21. Estimation of transfer functions: Asymptotic theory and a bound of model uncertainty