Universal approximation bounds for superpositions of a sigmoidal function

IEEE Transactions on Information Theory

Volumn 39, Issue 3, 1993, Pages 930-945

  Barron, Andrew R ^a  

^a YALE UNIVERSITY   (United States)

Author keywords

[No Author keywords available]

Indexed keywords

APPROXIMATION THEORY; FOURIER TRANSFORMS; FUNCTION EVALUATION; INFORMATION THEORY;

ARTIFICIAL NEURAL NETWORKS; FEEDFORWARD NETWORKS; SIGMOIDAL FUNCTIONS; UNIVERSAL APPROXIMATION BOUNDS;

NEURAL NETWORKS;

EID: 0027599793     PISSN: 00189448     EISSN: None     Source Type: Journal    
DOI: 10.1109/18.256500     Document Type: Article

References (33)

1. G. Cybenko Approximations by superpositions of a sigmoidal function Math. Contr. Signals, Syst. 2 303 314 1989
2. Κ. Hornik M. Stincheombe H. White Multi-layer feedforward networks are universal approximators Neural Networks 2 359 366 1989
3. A. Pinkus n-Widths in Approximation Theory 1985 Springer-Verlag New York
4. L. K. Jones A simple lemma on greedy approximation in Hilbert space and convergence rates for projection pursuit regression and neural network training Ann. Statist. 20 608 613 Mar. 1992
5. K.-Y. Siu J. Brunk On the power threshold circuits with small weights SIAM J. Discrete Math. 1991
6. N. M. Korobov Number Theoretic Methods of Approximate Analysis 1963 Fiznatgiz Moscow
7. G. Wahba Spline Models for Observational Data 1990 SIAM PA, Philadelphia
8. A. R. Barron Statistical properties of artificial neural networks Proc. IEEE Int. Conf. Decision Contr. 280 285 Proc. IEEE Int. Conf. Decision Contr. Tampa FL 1989-Dec.-13-15
9. A. R. Barron Nonparametric Functional Estimation 561 576 1991 Kluwer Academic The Netherlands, Dordrecht Complexity regularization with applications to artificial neural networks
10. A. R. Barron T. M. Cover Minimum complexity density estimation IEEE Trans. Inform. Theory IT-37 1034 1053 1991
11. A. R. Barron Approximation and estimation bounds for artificial neural networks Proc. 4th Annu. Workshop Computation. Learning Theory 243 249 Proc. 4th Annu. Workshop Computation. Learning Theory 1991-Aug.
12. H. White Connectionists nonparametric regression: Multilayer feedforward networks can learn arbitrary mappings Neural Networks 3 5 535 550 1990
13. D. Haussler Decision theoretic generalizations of the PAC model for neural net and other learning applications 1991 Santa Cruz UCSC-CRL-91-02 Univ. of California
14. A. R. Barron R. L. Barron Statistical learning networks: A unifying view Computing Science and Statistics: Proc. 21st Symp. Interface 192 203 Computing Science and Statistics: Proc. 21st Symp. Interface 1988
15. L. Breiman Hinging hyperplanes for regression, classification, and function approximation IEEE Trans. Inform. Theory 39 999 1013 May 1993
16. R. Tibshirani Slide functions for projection pursuit regression and neural networks 1992 9205 Univ. Toronto
17. Y. Zhao On projection pursuit learning 1992
18. F. Girosi G. Anzellotti Convergence rates of approximation by translates 1992 1288 Mass. Inst. Technol.
19. A Farago G. Lugosi Strong universal consistency of neural network classifiers 1992 Tech. Univ. Budapest
20. A. R. Barron Neural net approximation Proc. Yale Workshop Adaptive Learning Syst. Proc. Yale Workshop Adaptive Learning Syst. 1992-May
21. D. F. McCaffrey Convergence rates for single hidden layer feedforward networks 1992 CA, Santa Monica Dept. Statist., North Carolina State Univ.
22. H. N. Mhaskar C. A. Micchelli Approximation by superposition of a sigmoidal function Advances in Appl. Math. 13 350 373 1992
23. L. K. Jones Good weights and hyperbolic kernels for neural networks, projection pursuit, and pattern classification: Fourier strategies for extracting information from high-dimensional data 1991 Lowell Dept. Math. Sci., Univ. of Massachusetts
24. G. Pisier Remarques sur un resultat non publie de Β. Maurey Seminaire d' analyse fonctionelle 1980-1981 Seminaire d' analyse fonctionelle 1980-1981 Palaiseau
25. L. K. Jones Constructive approximations for neural networks by sigmoidal functions Proc. IEEE: Special Issue on Neural Networks 78 1586 1589 Proc. IEEE: Special Issue on Neural Networks 1991
26. E. Kushilevitz Y. Mansour Learning decision trees using the Fourier spectrum Proc. 23rd ACM Symp Theory Comput. 455 464 Proc. 23rd ACM Symp Theory Comput. 1991
27. M. Bellare The spectral norm of finite functions 1991 TR-465
28. W. Rudin Realand Complex Analysis 1984 McGraw-Hill New York
29. E. M. Stein G. Weiss Introduction to Fourier Analysis on Euclidean Spaces 1971 Princeton Univ. Press NJ, Princeton
30. C. Darken M. Donahue L. Gurvits E. Sontag Rate of approximation results motivated b robust neural network learning Proc. Sixth ACM Wrokshop on Computat. Learning Theory Proc. Sixth ACM Wrokshop on Computat. Learning Theory
31. J. Yukich Sup norm approximation bounds for networks via Vapnik-Chervonenkis classes Jan. 1993 Dept. of Math., Lehigh Univ. PA, Bethlehem
32. V. Kůrková Kolmogorov's theorem and multilayer neural networks Neural Net. 5 501 506 1992