Approximating functions by neural networks: A constructive solution in the uniform norm

Neural Networks

Volumn 9, Issue 6, 1996, Pages 965-978

  Meltser, Mark ^c   Shoham, Moshe ^c   Manevitz, Larry M ^a,b  

^a UNIVERSITY OF HAIFA   (Israel)

^b POLYTECHNIC UNIVERSITY   (United States)

^c University of Haifa ^*

Author keywords

approximating functions; artificial neural networks; constructive approximation; dynamic neural network architecture; feed forward; uniform norm

Indexed keywords

APPROXIMATION THEORY; BACKPROPAGATION; ERROR ANALYSIS; FUNCTIONS;

APPROXIMATING FUNCTIONS; CONSTRUCTIVE APPROXIMATION; NEURONS; UNIFORM NORM;

FEEDFORWARD NEURAL NETWORKS;

ARTICLE; ARTIFICIAL NEURAL NETWORK; MATHEMATICAL ANALYSIS; MOTOR CONTROL; POSITIVE FEEDBACK; PRIORITY JOURNAL;

EID: 0030220517     PISSN: 08936080     EISSN: None     Source Type: Journal    
DOI: 10.1016/0893-6080(95)00124-7     Document Type: Article

References (10)

1. Cybenko G. Approximation by superpositions of a sigmoidal function. Mathematics of Control Signals and Systems. 2:1989;303-314.
2. Danskin, J. (1967). The theory of max-min. New York: Springer-Verlag.
3. Gallant A.R., White H. On learning the derivatives on an unknown mapping with multilaery feedforward networks. Neural Networks. 5:1992;129-138.
4. Hornik K., Stinchcombe M., White H. Multilayer feedforward networks are universal approximation. Neural Networks. 2:1989;359-366.
5. Hornik K., Stinchcombe M., White H. Universal approximation of an unknown mapping and its derivatives. Neural Networks. 3:1990;551-560.
6. Leshno M., Lin V., Pinkus A., Schocken S. Multilayer feedforward networks with non-polynomial activation functions can approximate any continuous function. Neural Networks. 6(3):1993;861-867.
7. Rumelhart, D.E., Hinton, G.E., & Williams, R.J. (1986). Learning internal representations by error propagation. In D.E. Rumelhard & J.L. McClelland (Eds.), Parallel distributed processing: explorations in the microstructure of cognition 1 (pp. 318-362). Cambridge, MA: MIT Press.
8. Shoham M., Li C., Hacham Y., Kriendler E. Neural network control of robot arm. CIRP Annals. 41(1):1992;407-410.
9. Shoham, M., Meltser, M., & Manevitz, L. (in preparation). Controlling a 2-degree of freedom robot arm via maximal error training.
10. Werbos, P.J. (1974). Beyond regression: New tools for prediction and analysis in the behavioral sciences. Doctoral Dissertation, Appl. Math., Harvard University, November.