Approximation of continuous functions of several variables by an arbitrary nonlinear continuous function of one variable, linear functions, and their superpositions

Applied Mathematics Letters

Volumn 11, Issue 3, 1998, Pages 45-49

  Gorban', A N ^a  

^a NONE

Author keywords

Approximation; Neural networks; Superposition; Weierstrass theorem

Indexed keywords

EID: 0002271590     PISSN: 08939659     EISSN: None     Source Type: Journal    
DOI: 10.1016/S0893-9659(98)00032-9     Document Type: Article

References (13)

1. M.N. Stone, The generalized Weierstrass approximation theorem, Math. Mag. 21, 167-183, 237-254 (1948).
2. A.N. Kolmogorov, On representation of continuous functions of several variables by superpositions of continuous functions of smaller number of variables, Dokl. AN SSSR 108 (2), 179-182 (1956).
3. V.I. Arnold, On the functions of three variables, Dokl. AN SSSR 114 (4), 679-681 (1957).
4. A.N. Kolmogorov, On representation of continuous functions of several variables as superpositions of continuous functions of one variable, Dokl. AN SSSR 114 (5), 953-956 (1957).
5. R. Pfeifer, Z. Schreter, F. Fogelman-Soulie and L. Steels, Editors, Connectionism in Perspective, North-Holland, (1989).
6. A.N. Gorban, Training Neural Networks, USSR-USA JV "ParaGraph", Moscow, (1990); English translation, AMSE Transaction, Scientific Siberian, A, Volume 6, Neurocomputing, pp. 1-134, Tassin, France, (1993).
7. A.N. Gorban, Training Neural Networks, USSR-USA JV "ParaGraph", Moscow, (1990); English translation, AMSE Transaction, Scientific Siberian, A, Volume 6, Neurocomputing, pp. 1-134, Tassin, France, (1993).
8. J.M. Zurada, Introduction to Artificial Neural Systems, PWS Publishing, (1992).
9. G. Cybenko, Approximation by superposition of a sigmoidal function, Mathematics of Control, Signals, and Systems 2, 303-314 (1989).
10. K. Hornik, M. Stinchcombe and H. White, Multilayer feedforward networks are universal approximators, Neural Networks 2, 359-366 (1989).
11. D.A. Kochenov and D.A. Rossiev, Approximations of functions of C[A, B] class by neural-net predictors (architectures and results), AMSE Transaction, Scientific Siberian, A, Volume 6, Neurocomputing, pp. 189-203, Tassin, France, (1993).
12. J. Wiedermann, On the computation efficiency of symmetric neural networks, Theor. Comput. Sci. 80 (2), 337-345 (1991).
13. S.E. Gilev and A.N. Gorban, On completeness of the class of functions computable by neural networks, Proc. of the World Congress on Neural Networks (WCNN'96), Sept. 15-18, 1996, San Diego, CA, pp. 984-991, Lawrens Erlbaum Accociates, (1996).