Universal approximation in p-mean by neural networks

Neural Networks

Volumn 11, Issue 4, 1998, Pages 661-667

  Burton, Robert M ^a   Dehling, Herold G ^b  

^a OREGON STATE UNIVERSITY   (United States)

^b UNIVERSITY OF GRONINGEN   (Netherlands)

Author keywords

Approximation theory; L(p) approximation; Neural networks; Single hidden layer network; Universal transfer functions

Indexed keywords

APPROXIMATION THEORY; DATA STRUCTURES; GRAPH THEORY; MATHEMATICAL TRANSFORMATIONS; TRANSFER FUNCTIONS;

UNIVERSAL APPROXIMATION; UNIVERSAL TRANSFER FUNCTION;

FEEDFORWARD NEURAL NETWORKS;

ARTICLE; MATHEMATICAL ANALYSIS; NERVE CELL; NERVE CELL NETWORK; PRIORITY JOURNAL; PROBABILITY; SYNAPTIC TRANSMISSION; THEORY;

EID: 0032099977     PISSN: 08936080     EISSN: None     Source Type: Journal    
DOI: 10.1016/S0893-6080(98)00009-4     Document Type: Article

References (7)

1. Cybenko G. Approximation by superpositions of a sigmoidal function. Math. Control, Signals, Systems. 2:1989;303-314.
2. Funahashi K. On approximate realization of continuous mappings by neural networks. Neural Networks. 2:1989;183-192.
3. Gallant, A.R., White, H. (1988). There exists a neural network that does not make avoidable mistakes. In: Proceedings of Second IEEE International Conference on Neural Networks, Vol. I. SOS Printing, San Diego, CA, pp. 657-664.
4. Hornik K. Approximation capabilities of multilayer feedforward net-works. Neural Networks. 4:1991;251-257.
5. Hornik K. Multilayer feedforward networks are universal approximators. Neural Networks. 2:1989;359-366.
6. Leshno M., Lin V.Y., Pinkus A., Schocken S. Multilayer feedforward networks with a nonpolynomial activation function can approximate any function. Neural Networks. 6:1993;861-867.
7. Schwartz, L. (1966). Theorie des Distributions. Hermann, Paris.