Neural networks with a continuous squashing function in the output are universal approximators

Neural Networks

Volumn 13, Issue 6, 2000, Pages 561-563

  Castro, J L ^a   Mantas, C J ^a   Benitez J M ^a  

^a UNIVERSITY OF GRANADA   (Spain)

Author keywords

Continuous functions; Feedforward networks; Squashing functions; Universal approximation

Indexed keywords

APPROXIMATION THEORY; FEEDFORWARD NEURAL NETWORKS; FUNCTIONS; MATHEMATICAL MODELS; MATHEMATICAL TRANSFORMATIONS; THEOREM PROVING;

BOREL FUNCTIONS; CONTINUOUS FUNCTIONS; SQUASHING FUNCTIONS; UNIVERSAL APPROXIMATORS;

MULTILAYER NEURAL NETWORKS;

ACCURACY; ARTICLE; ARTIFICIAL NEURAL NETWORK; MATHEMATICAL ANALYSIS; MATHEMATICAL COMPUTING; PRIORITY JOURNAL;

NEURAL NETWORKS (COMPUTER);

EID: 0034233437     PISSN: 08936080     EISSN: None     Source Type: Journal    
DOI: 10.1016/S0893-6080(00)00031-9     Document Type: Article

References (15)

1. Attali J., Pages G. Approximations of functions by a multilayer perceptron. Neural Network. 10:(6):1997;1069-1081.
2. Bissessur Y., Naguib R. Buried plant detection: a Volterra series modelling approach using artificial neural networks. Neural Networks. 9:(6):1995;1045-1060.
3. Cardaliaguet P., Euvrard G. Approximation of a function and its derivative with a neural network. Neural Networks. 5:(2):1992;207-220.
4. Funahashi K. On the approximate realization of continuous mappings by neural networks. Neural Networks. 2:1989;183-192.
5. Han Y., Xiu L., Wang Z., Chen Q., Tan S. Artificial neural networks controlled fast valving in a power generation plant. IEEE Transactions on Neural Networks. 8:(2):1987.
6. Hornik K. Approximation capabilities of multilayer feedforward networks. Neural Networks. 4:(2):1991;251-257.
7. Hornik K. Some new results on neural network approximation. Neural Networks. 6:(8):1993;1069-1072.
8. Hornik K., Stinchcombe M., White H. Multilayer feedforward networks are universal approximators. Neural Networks. 2:1989;359-366.
9. Kurkova V. Approximation of functions by perceptron networks with bounded number of hidden units. Neural Networks. 8:(5):1995;745-750.
10. Leshno M., Liu V., Pinkus A., Shocken S. Multilayer feedforward networks with a nonpolynomial activation function can approximate any function. Neural Networks. 6:(6):1993;861-867.
11. Leyva R., Martinez-Salamero L., Jammes B., Marpinard J., Guinjoan F. Identification and control of power converters by means of neural networks. IEEE Transactions on Circuits and Systems-I: Fundamental Theory and Applications. 44:(8):1997.
12. Meltser M., Shoham M., Manevitz L. Approximations of functions by a multilayer perceptron: a new approach. Neural Networks. 10:(6):1997;1069-1081.
13. Moody J., Antsaklis P. The dependence identification neural network construction algorithm. IEEE Transactions on Neural Networks. 7:(1):1996.
14. Sietsma J., Dow J. Creating artificial neural networks that generalize. Neural Networks. 4:(1):1991;67-79.
15. Spall J., Cristion J. A neural network controller for systems with unmodeled dynamics with applications to wastewater treatment. IEEE Transactions on Systems, Man and Cybernetics-Part B:Cybernetics. 27:(3):1997.