The errors of approximation for feedforward neural networks in the Lp metric

Mathematical and Computer Modelling

Volumn 49, Issue 7-8, 2009, Pages 1563-1572

  Cao, Feilong ^a   Zhang, Rui ^b,c  

^a CHINA JILIANG UNIVERSITY   (China)

^b XI'AN JIAOTONG UNIVERSITY   (China)

^c NORTHWEST UNIVERSITY   (China)

Author keywords

Approximation; Estimate of error; Lp metric; Neural networks

Indexed keywords

NUMBER THEORY;

APPROXIMATION; APPROXIMATION COMPLEXITY; ESTIMATE OF ERROR; HIDDEN LAYERS; HIDDEN NODES; INTEGRABLE FUNCTIONS; LP METRIC; MEAN FUNCTIONS; MODULUS OF SMOOTHNESS; NOVEL METHODS; TARGET FUNCTIONS;

FEEDFORWARD NEURAL NETWORKS;

EID: 60949114168     PISSN: 08957177     EISSN: None     Source Type: Journal    
DOI: 10.1016/j.mcm.2008.07.031     Document Type: Article

References (19)

1. Ahues M., Largillier A., and Amosov A. Superconvergence of projection methods for weakly singular integral operators. In: Constanda C., and Potapenko S. (Eds). Integral Methods in Science and Engineering (2008), Birkhäuser Verlag, Boston 1-8
2. Barron A.R. Universal approximation bounds for superpositions of a sigmoidal function. IEEE Trans. Inform. Theory 39 (1993) 930-945
3. Bergh J., and Löfström L. Interpolation Space (1976), Springer-Verlag, Berlin
4. Cao F.L., Xu Z.B., and Li Y.M. Pointwise approximation for neural networks. Lect. Notes Comput. Sci. 3496 (2005) 39-44
5. Cao F.L., Xie T.F., and Xu Z.B. The estimate for approximation error of neural networks: A constructive approach. Neurocomputing 71 (2008) 626-630
6. Chen T.P., and Chen H. Universal approximation to nonlinear operators by neural networks with arbitrary activation functions and its application to a dynamic system. IEEE Trans. Neural Netw. 6 (1995) 911-917
7. n) by multilayer feedforward networks and related problems. IEEE Trans. Neural Netw. 6 (1995) 25-30
8. Chui C.K., and Li X. Approximation by ridge functions and neural networks with one hidden layer. J. Approx. Theory 70 (1992) 131-141
9. Cybenko G. Approximation by superpositions of sigmoidal function. Math. Control Signal Systems 2 (1989) 303-314
10. Funahashi K.I. On the approximate realization of continuous mappings by neural networks. Neural Netw. 2 (1989) 183-192
11. Hornik K., Stinchombe M., and White H. Multilayer feedforward networks are universal approximation. Neural Netw. 2 (1989) 359-366
12. Leshno M., Lin V.Y., Pinks A., and Schocken S. Multilayer feedforward networks with a nonpolynomial activation function can approximate any function. Neural Netw. 6 (1993) 861-867
13. Llanas B., and Sainz F.J. Constructive approximate interpolation by neural networks. J. Comput. Appl. Math. 188 (2006) 283-308
14. Lorentz G.G. Approximation of Functions (1966), Rinehart and Winston, New York
15. d) by neural and mixture networks. IEEE Trans. Neural Netw. 9 (1998) 969-978
16. Makovoz Y. Uniform approximation by neural networks. J. Approx. Theory 95 (1998) 215-228
17. Mhaskar H.N., and Miccheli C.A. Degree of approximation by neural networks with a single hidden layer. Adv. Appl. Math. 16 (1995) 151-183
18. Suzuki S. Constructive function approximation by three-layer artificial neural networks. Neural Netw. 11 (1998) 1049-1058
19. Xu Z.B., and Cao F.L. The essential order of approximation for neural networks. Sci. China Ser. F 47 (2004) 97-112