On the partitioning capabilities of feedforward neural networks with sigmoid nodes

Neural Computation

Volumn 15, Issue 10, 2003, Pages 2457-2481

  Koutroumbas, K ^a  

^a NATIONAL OBSERVATORY OF ATHENS   (Greece)

Author keywords

[No Author keywords available]

Indexed keywords

ARTICLE; ARTIFICIAL NEURAL NETWORK; BIOLOGICAL MODEL; MATHEMATICS;

MATHEMATICS; MODELS, NEUROLOGICAL; NEURAL NETWORKS (COMPUTER);

EID: 0041360336     PISSN: 08997667     EISSN: None     Source Type: Journal    
DOI: 10.1162/089976603322362437     Document Type: Article

References (22)

1. Castro, J. L., Mantas, C. J., & Benitez, J. M. (2000). Neural networks with a continuous squashing function in the output are universal approximators. Neural Networks, 13, 561-563.
2. Chen, T., & Chen, H. (1993). Approximation of continuous functionals by neural networks with application to dynamic systems. IEEE Transactions on Neural Networks, 4(5), 910-918.
3. n) by multilayer feedforward networks and related problems. IEEE Transactions on Neural Networks, 6(1), 25-31.
4. Chen, T., & Chen, H. (1995b). Universal approximation to nonlinear operators by neural networks with arbitrary activation functions and its application to dynamical systems. IEEE Transactions on Neural Networks, 6(4), 911-917.
5. Cybenko, G. (1989). Approximation by superpositions of a sigmoidal function. Mathematics of Control, Signals and Systems, 2, 304-314.
6. Gibson, G. J., & Cowan, C. F. N. (1990). On the decision regions of multilayer perceptrons. Proceedings of the IEEE, 78(10), 1590-1594.
7. Hornik, K., Stinchcombe, M., & White, H. (1989). Multilayer feedforward networks are universal approximators. Neural Networks, 2(5), 359-366.
8. Ito, Y. (1991). Representation of functions by superpositions of a step or sigmoid function and their applications to neural network theory. Neural Networks, 4(3), 385-394.
9. Kalouptsidis, N. (1997). Signal processing systems, theory and design. New York: Wiley.
10. Lippmann, R. P. (1987). An introduction to computing with neural networks. IEEE ASSP Magazine, 4(2), 4-22.
11. Makhoul, J., El-Jaroudi, A., & Schwartz, R. (1991). Partitioning capabilities of two-layer neural networks. IEEE Transactions on Signal Processing, 39(6), 1435-1440.
12. Manitez, J. M., Castro, J. L., & Requena, I. (1997). Are neural networks black-boxes? IEEE Transactions on Neural Networks, 8(5), 1156-1164.
13. Minsky, M. L., & Papert, S. A. (1988). Perceptrons (exp. ed.). Cambridge, MA: MIT Press.
14. Nilsson, N. (1965). Learning machines. New York: McGraw-Hill.
15. Rosenblatt, F. (1958). The perception: A probabilistic model for information storage and organization in the brain. Psychological Review, 65, 386-408.
16. Sandberg, I. W. (1994). General structures for classification. IEEE Transactions on Circuits and Systems I, 41(5), 372-376.
17. Sandberg, I. W. (1999). A note on classification and the approximation of functionals. International Journal of Circuit Theory and Applications, 27, 443-445.
18. Sandberg, I. W. (2001). Gaussian radial basis functions and inner-product spaces. Circuits, Systems and Signal Processing, 20, 635-642 (errata in Vol. 21, no. 1, p. 123, 2002).
19. Sandberg, I. W., Lo, J. T., Fancourt, C. L., Principe, J., Shigeru, S., & Haykin, S. (2001). Nonlinear dynamical systems: Feedforward neural network perspectives. New York: Wiley.
20. Shonkwiler, R. (1993). Separating the vertices of N-cubes by hyperplanes and its application to artificial neural networks. IEEE Transactions on Neural Networks, 4(2), 343-347.
21. Theodoridis, S., & Koutroumbas, K. (1998). Pattern recognition. San Diego, CA: Academic Press.
22. Williamson, R. C., & Helinke, U. (1995). Existence and uniqueness results for neural network approximations. IEEE Transactions on Neural Networks, 6(1), 2-14.