The complexity of model classes, and smoothing noisy data

Systems and Control Letters

Volumn 34, Issue 3, 1998, Pages 133-140

  Bartlett, Peter L ^a   Kulkarni, Sanjeev R ^b  

^a AUSTRALIAN NATIONAL UNIVERSITY   (Australia)

^b Princeton University   (United States)

Author keywords

Computational learning theory; Covering numbers; Smoothing; System identification

Indexed keywords

EID: 0000268018     PISSN: 01676911     EISSN: None     Source Type: Journal    
DOI: 10.1016/S0167-6911(98)00008-5     Document Type: Article

References (13)

1. A.R. Barron, Universal approximation bounds for super-position of a sigmoidal function, IEEE Trans. Inform. Theory 39 (1993) 930-945.
2. P.L. Bartlett, Pattern classification in neural networks: the size of the weights is more important than the size of the network, IEEE Trans. Inform. Theory, March 1998, to appear.
3. P.L. Bartlett, S.R. Kulkarni, Signal restoration for general function classes, Tech. Report, 1998, in preparation.
4. P.L. Bartlett, S.R. Kulkarni, A universally consistent estimator with deterministic data conditions, Tech. Report, 1998, in preparation.
5. B. Dasgupta, E.D. Sontag, Sample complexity for learning recurrent perceptron mappings, IEEE Trans. Inform. Theory 42 (1996) 1479-1487.
6. P.W. Goldberg, M.R. Jerrum, Bounding the Vapnik-Chervonenkis dimension of concept classes parametrized by real numbers, Mach. Learning 18 (2/3) (1995) 131-148.
7. D. Haussler, Decision theoretic generalizations of the PAC model for neural net and other learning applications, Inform. Comput. 100 (1992) 78-150.
8. A.N. Kolmogorov, V.M. Tihomirov, ε-entropy and ε-capacity of sets in functional spaces, AMS Translations Ser. 2, 17 (1961) 277-364.
9. S.R. Kulkarni, S.E. Posner, Rates of convergence of nearest neighbor estimation under arbitrary sampling, IEEE Trans. Inform. Theory 39 (1995) 1028-1039.
10. S.R. Kulkarni, S.E. Posner, Universal prediction of nonlinear systems, in: Proc. 34th Conf. on Decision and Control, 1995, pp. 4024-4029.
11. W.S. Lee, P.L. Bartlett, R.C. Williamson, Efficient agnostic learning of neural networks with bounded fan-in, IEEE Trans. Inform. Theory 42 (1996) 2118-2132.
12. D. Pollard, Convergence of Stochastic Processes, Springer, Berlin, 1984.
13. G. Zames, J.G. Owen, A note on metric dimension and feedback in discrete time, IEEE Trans. Automat. Control 38 (4) (1993) 664-667.