Exact classification with two-layer neural nets in n dimensions

Discrete Applied Mathematics

Volumn 81, Issue 1-3, 1998, Pages 19-39

  Sweatman, Catherine Z W Hassell ^a   Gibson, Gavin J ^b   Mulgrew, Bernard ^a  

^a UNIVERSITY OF EDINBURGH   (United Kingdom)

^b BIOMATHEMATICS AND STATISTICS SCOTLAND   (United Kingdom)

Author keywords

Exact classification; McCulloch Pitts units; Neural networks

Indexed keywords

EID: 0041353881     PISSN: 0166218X     EISSN: None     Source Type: Journal    
DOI: 10.1016/S0166-218X(97)00053-X     Document Type: Article

References (23)

1. E. Amaldi, E. Mayoraz, D. de Werra, A review of combinatorial problems arising in feedforward neural network design, Discrete Appl. Math. 52 (1994) 111-138.
2. E.K. Blum, L.K. Li, Approximation theory and feedforward networks. Neural Networks 4 (1991) 511-515.
3. G. Brightwell, C. Kenyon, H. Paugam-Moisy, Multilayer neural networks: one or two hidden layers?, CDAM Research report CDAM-96-20, Centre for Discrete and Applicable Mathematics, LSE.
4. M. Budinich, E. Milotti, Properties of feedforward neural networks, J. Phys. A 25 (1992) 1903-1914.
5. M. Cosnard, P. Koiran, H. Paugam-Moisy, A step towards the frontier between one-hidden-layer and two-hidden-layer neural networks, in: Proc. International Joint Conference on Neural Networks, Nagoya, Japan, October, 1993.
6. G. Cybenko, Approximations by superpositions of a sigmoidal function, Math. Control Signals Systems 2 (1972) 303-314.
7. K.-L. Funahashi, On the approximate realisation of continuous mappings by neural networks, Neural Networks 2 (1989) 183-192.
8. G.J. Gibson, C. F.N. Cowan, On the decision regions of multilayer perceptrons, in: Proceedings of IEEE 78, 1990, pp. 1590-1594.
9. G.J. Gibson, A combinatorial approach to understanding perceptron decision regions, IEEE Trans. Neural Networks 4 (1993) 989-992.
10. G.J. Gibson, Exact classification with two-layer neural nets, J. Comput. Syst. Sci. 52 (2) (1996) 349-356.
11. K. Hornik, M. Stinchcombe, H. White, Multilayer feed-forward networks are universal approximators, Neural Networks 2 (1989) 359-366.
12. S.-C. Huang, Y.-F. Huang, Bounds on the number of hidden neurons in multilayer preceptrons, IEEE Trans. Neural Networks 2 (1991) 47-55.
13. W.H. Huang, R.P. Lippmann, Neural nets and traditional classifiers, in: Proceedings of Conference on Neural Information Processing Systems, Denver, CO, November, 1987, pp. 387-396.
14. L.K. Li, On computing decision regions with neural nets, J. Comput. Syst. Sci. 43 (1991) 509-512.
15. R.P. Lippmann, An introduction to computing with neural nets, IEEE ASSP Mag. 4 (2) (1987) 4-22.
16. W.S. McCulloch, W. Pitts, A logical calculus of the ideas imminent in nervous activity, Bull. Math. Biophys. 5 (1943) 115-133.
17. J. Makhoul, R. Schwartz, A. El-Jaroudi, Classification capabilities of two-layer neural nets, in: Proceedings of IEEE International Conference ASSP, Glasgow, (1989), pp. 653-638.
18. R. Shonkwiler, Separating the vertices of N-Cubes by hyperplanes and its application to artificial neural networks, IEEE Trans. Neural Networks 4 (1993) 343-347.
19. E.D. Sontag, Feedforward nets for interpolation and classification, J. Comput. Syst. Sci. 45 (1992) 20-48.
20. H. Takahashi, E. Tomita, T. Kawabata, Separability of internal representations in multilayer perceptrons with application to learning, Neural Networks 6 (1993) 689-703.
21. B. Widrow, R.G. Winter, R.A. Baxter, Layered neural nets for pattern recognition, IEEE Trans. Acoust. Speech Signal Process 36 (1988) 1109-1118.
22. A. Wieland, R. Leighton, Geometric analysis of neural network capabilities, in: Proceeding of 1st International Conference on Neural Nets, vol. 2. IEEE, San Diego, CA, June, 1987 pp. 754-756.
23. P.J. Zwietering, The complexity of multi-layered perceptrons, Ph.D. Thesis, Technische Universiteit Eindhoven, 1994.