Comparing neural network approximations for different functional forms

Expert Systems

Volumn 16, Issue 2, 1999, Pages 60-71

  Morgan, Peter ^a   Curry, Bruce ^a   Beynon, Malcolm ^a  

^a CARDIFF UNIVERSITY   (United Kingdom)

Author keywords

[No Author keywords available]

Indexed keywords

APPROXIMATION THEORY; FUNCTIONS; MATHEMATICAL MODELS; MULTILAYER NEURAL NETWORKS;

HIDDEN LAYERS; RADIAL BASIS FUNCTION NETWORKS; UNIVERSAL APPROXIMATION;

FEEDFORWARD NEURAL NETWORKS;

EID: 0032648867     PISSN: 02664720     EISSN: None     Source Type: Journal    
DOI: 10.1111/1468-0394.00096     Document Type: Article

References (11)

1. CARLEY, A.F. and P.H. MORGAN (1989) Computational Methods in the Chemical Sciences, Chichester: Ellis Horwood.
2. CICHOCKI, A. and R. UNBEHAUEN (1992) Neural Networks for Optimisation and Signal Processing, Chichester: Wiley.
3. CIUCA, I. and J.A. WARE (1997) Layered neural networks as universal approximators, Lecture Notes in Computer Science, 1226, 411-415.
4. CURRY, B., P.H. MORGAN and M.J. BEYNON (1996) Neural networks and flexible approximations, 3rd International Conference on Neural Methods in Management Science and Economics (ACSEG), Nantes.
5. CYBENKO, G. (1989) Approximation by superpositions of a sigmoid function, Mathematics of Control, Signals and Systems, 2, 303-314.
6. HORNIK, K., M. STINCHCOMBE and H. WHITE (1989) Multi-layer feedforward networks are universal approximators, Neural Networks, 2(5), 359-366.
7. ITO Y. (1994) Approximation capability of layered neural networks with sigmoid units on two layers, Neural Computation, 6, 1233-1243.
8. KURKOVA, V. (1992) Kolmogorov's theorem and multi-layer neural networks, Neural Networks, 5, 501-506.
9. MOON, Y.-J. and S.-Y. OH (1996) A constructive design method for two layer perceptrons and its application to the design of modular neural networks, Expert Systems, 13(3), 183-194.
10. MULIER, F. and V. CHERKASSY (1995) Self-organisation as an iterative kernel smoothing process, Neural Computation, 8, 164-177.
11. TAMURA, S. and M. TATEISHI (1997) Capabilities of a four-layered feedforward neural network: four layers versus three, IEEE Transactions on Neural Networks, 8, 251-255.