Integral combinations of Heavisides

Mathematische Nachrichten

Volumn 283, Issue 6, 2010, Pages 854-878

  Kainen, Paul C ^a   Kůrková, Věra ^b   Vogt, Andrew ^a  

^a GEORGETOWN UNIVERSITY   (United States)

^b INSTITUTE OF COMPUTER SCIENCE   (Czech Republic)

Author keywords

Feedforward neural network; Function of controlled decay; Green's function for iterated Laplacians; Heaviside function; Integral formula; Order of vanishing; Perceptron; Plane wave; Radon transform

Indexed keywords

EID: 77954163756     PISSN: 0025584X     EISSN: 15222616     Source Type: Journal    
DOI: 10.1002/mana.200710029     Document Type: Article

References (20)

1. A. R. Barron, Universal approximation bounds for superposition of a sigmoidal function, IEEE Trans. Inform. Theory 39, 930-945 (1993).
2. N. Bleistein and R. A. Handelsman, Asymptotic Expansions of Integrals (Holt, Rinehart & Winston, New York, 1975).
3. R. C. Buck, Advanced Calculus (McGraw-Hill, New York, 1965).
4. S.M. Carroll and B.W. Dickinson, Construction of neural nets using the Radon transform, in: Proceedings of the IJCNN Conference, Washington, D. C., June 18-22, 1989 (IEEE Press, New York, 1989), pp. I. 607-611.
5. R. Courant and D. Hilbert, Methods of Mathematical Physics, Vol. 2 (Wiley, New York, 1962).
6. B. Davies, Integral Transforms and their Applications, 2nd Edition (Springer, New York, 1985).
7. H. Engels, Numerical Quadrature and Cubature (Academic Press, London, 1980).
8. K. Funahashi, On the approximate realization of continuous mappings by neural networks, Neural Networks 2, 183-192 (1989).
9. I. M. Gel'fand, M. I. Graev, and N. Ya. Vilenkin, Generalized Functions, Vol. 5 (Academic Press, New York, 1966).
10. F. Girosi and G. Anzellotti, Rates of convergence for radial basis function and neural networks, in: Artificial Neural Networks for Speech and Vision (Chapman & Hall, London, 1993), pp. 97-113.
11. S. Helgason, The Radon Transform (Birkhäuser, Boston, 1980).
12. E. Hewitt and K. Stromberg, Real and Abstract Analysis (Springer-Verlag, New York, 1965).
13. Y. Ito, Representation of functions by superpositions of a step or sigmoid function and their applications to neural network theory, Neural Networks 4, 385-394 (1991).
14. P. C. Kainen, V. Kůrková, and A. Vogt, Best approximation by linear combinations of characteristic functions of half spaces, J. Approx. Theory 122, 151-159 (2003).
15. P. C. Kainen, V. Kůrková, and A. Vogt, Geometry and topology of continuous best and near best approximations, J. Approx. Theory 105, 252-262 (2000).
16. P. C. Kainen, V. Kůrková, and A. Vogt, An integral formula for Heaviside neural networks, Neural Network World 3, 313-319 (2000).
17. P. C. Kainen, V. Kůrková, and A. Vogt, Best approximation by Heaviside perceptron networks, Neural Networks 13, 695-697 (2000).
18. P. C. Kainen, V. Kůrková, and A. Vogt, Approximation by neural networks is not continuous, Neurocomputing 29, 47-56 (1999).
19. V. Kůrková, P. C. Kainen, and V. Kreinovich, Estimates of the number of hidden units and variation with respect to half-spaces, Neural Networks 10, 1061-1068 (1997).
20. A. H. Zemanian, Distribution Theory and Transform Analysis (Dover, New York, 1987).