Approximation by neural networks with a bounded number of nodes at each level

Journal of Approximation Theory

Volumn 122, Issue 2, 2003, Pages 260-266

  Gripenberg, Gustaf ^a  

^a AALTO UNIVERSITY   (Finland)

Author keywords

Approximation; Multilayer; Network; Neural

Indexed keywords

EID: 0038686384     PISSN: 00219045     EISSN: None     Source Type: Journal    
DOI: 10.1016/S0021-9045(03)00078-9     Document Type: Article

References (10)

1. M. Burger, A. Neubauer, Error bounds for approximation with neural networks, J. Approx. Theory 112 (2) (2001) 235-250.
2. A.N. Gorban', Approximation of continuous functions of several variables by an arbitrary nonlinear continuous function of one variable, linear functions, and their superpositions, Appl. Math. Lett. 11 (3) (1998) 45-49.
3. M. Leshno, V.Y. Lin, A. Pinkus, S. Schocken, Multilayer feedforward networks with a nonpolynomial activation function can approximate any function, Neural Networks 6 (1993) 861-867.
4. G.G. Lorentz, M.V. Golitschek, Y. Makovoz, Constructive Approximation, Advanced Problems, Springer, Berlin, 1996.
5. V. Maiorov, A. Pinkus, Lower bounds for approximation by MLP neural networks, Neurocomputing 25 (1-3) (1999) 81-91.
6. Y. Makovoz, Uniform approximation by neural networks, J. Approx. Theory 95 (2) (1998) 215-228.
7. A. Pinkus, Approximation theory of the MLP model in neural networks, in: Acta Numerica, Vol. 8, Cambridge University Press, Cambridge, 1999, pp. 143-195.
8. F. Scarselli, A.C. Tsoi, Universal approximation using feedforward neural networks: a survey of some existing methods and some new results, Neural Networks 11 (1998) 15-37.
9. S. Tamura, M. Tateish, Capabilities of four-layered feedforward neural network: four layers versus three, IEEE Trans. Neural Networks 8 (2) (1997) 251-255.
10. J. de Villiers, D. Barnard, Backpropagation neural nets with one and two hidden layers, IEEE Trans. Neural Networks 4 (12) (1992) 136-141.