Universal approximation using feedforward neural networks: A survey of some existing methods, and some new results

Neural Networks

Volumn 11, Issue 1, 1998, Pages 15-37

  Scarselli, Franco ^a   Chung Tsoi, Ah ^a  

^a NONE

Author keywords

Approximation by neural networks; Approximation of polynomials; Constructive approximation; Feedforward neural networks; Multilayer neural networks; Radial basis functions; Universal approximation

Indexed keywords

APPROXIMATION THEORY; LEARNING ALGORITHMS; POLYNOMIALS;

CONSTRUCTIVE APPROXIMATION; RADIAL BASIS FUNCTIONS;

FEEDFORWARD NEURAL NETWORKS;

ALGORITHM; ARTICLE; DIAGNOSTIC ACCURACY; NERVE CELL NETWORK; POSITIVE FEEDBACK; PRIORITY JOURNAL;

EID: 0345195977     PISSN: 08936080     EISSN: None     Source Type: Journal    
DOI: 10.1016/S0893-6080(97)00097-X     Document Type: Article

References (29)

1. Abramovitz, M. and Stegun, I. (1968). Handbook of mathematical functions. New York: Dover.
2. Albus J. A new approach to manipulator control: the cerebellar model articulation controller (cmac). Transactions of ASME. Journal of Dynamic Systems, Measurement and Control. 97:1975;220-227.
3. Barron A. Universal approximation bounds for superposition of a sigmoidal function. IEEE Transactions on Information Theory. 3:1993;930-945.
4. Blum E., Li K. Approximation theory and feedforward networks. Neural Networks. 4:1991;511-515.
5. Carroll, S. and Dickinson, B. (1989). Construction of neural networks using the Radon transform. IEEE International Conference on Neural Networks, vol. 1. Washington, DC: IEEE, pp. 607-611.
6. n) by multilayer feedforward networks and related problems. IEEE Transactions on Neural Networks. 6(1):1995;25-30.
7. Chui C., Li X. Approximation by ridge functions and neural networks with one hidden layer. Journal of Approximation Theory. 70:1992;131-141.
8. Chung K., Yao T. On lattices admitting a unique lagrange interpolations. SIAM Journal of Numerical Analysis. 14:1977;735-743.
9. Cybenko G. Approximation by superpositions of a sigmoidal function. Mathematics of Control, Signals, and Systems. 3:1989;303-314.
10. Geva S., Sitte J. A constructive method for multivariate function approximation by multilayered pereeptrons. IEEE Transactions on Neural Networks. 3(4):1992;621-623.
11. Hecht-Nielsen, R. (1989). Kolmogorov's mapping neural network existence theorem. In International Joint Conference on Neural Networks, vol. 3. Washington, DC: IEEE, pp. 11-14.
12. Hornik K. Approximation capabilities of multilayer feedforward neural networks. Neural Networks. 4:1990;251-257.
13. Hornik K. Some results on neural network approximation. Neural Networks. 6:1993;1069-1072.
14. Ito Y. Approximation of functions on a compact set by finite sums of sigmoid function without scaling. Neural Networks. 4:1991;817-826.
15. Katsuura H., Sprecher D.A. Computational aspects of Kolmogorov's superposition theorem. Neural Networks. 7(3):1994;455-461.
16. Kreinovich V. Arbitrary nonlinearity is sufficient to represent all functions by neural networks: a theorem. Neural Networks. 4:1991;381-383.
17. Kurkova V. Kolmogorov's theorem and multilayer neural networks. Neural Networks. 5:1992;501-506.
18. Lee S., Philips G. Construction of lattices for lagrange interpolation in projective space. Constructive Approximation. 7:1991;283-297.
19. Leshno M., Lin V., Pinkus A., Shocken S. Multilayer feedforward networks with a polynomial activation function can approximate any function. Neural Networks. 6:1993;861-867.
20. Mhaskar H., Micchelli C. Approximation by superposition of sigmoidal and radial basis functions. Advances in Applied Mathematics. 13:1992;350-373.
21. Mhaskar H., Micchelli C. Dimension independent bounds on the degree of approximation by neural networks. IBM Journal of Research and Development. 38(3):1994;277-283.
22. Nicolaides R. On a class of finite elements generated by lagrange interpolation. SIAM Journal of Numerical Analysis. 9:1972;435-445.
23. Park J., Sandberg I.W. Universal approximation using radial-basis-function networks. Neural Computation. 3(2):1991;246-257.
24. Park J., Sandberg I.W. Approximation and radial-basis-functions networks. Neural Computation. 5:1993;305-316.
25. Rudin, W. (1991). Principle of mathematical analysis, Sections 6 and 11.5. New York: McGraw-Hill.
26. Saseetharan M., Moody M. A modified neuron model that scales and resolve network paralysis. Network. 3:1992;101-104.
27. Sontag, E. (1991). Remarks on interpolation and recognition using neural nets. In Lippmann, R., Moody, J. and Touretzky, D. (Eds.), Advances in neural information processing system 3. San Matteo, CA: Morgan Kaufmann.
28. Sprecher D.A. On the structure of continuous functions of several variables. Transactions of the American Math Society. 115:1965;340-355.
29. Widrow B. 30 years of adaptive neural networks: Perceptron, Madaline, and Backpropagation. IEEE Transactions on Neural Networks. 78(9):1990;1415-1442.