A neural network of smooth hinge functions

IEEE Transactions on Neural Networks

Volumn 21, Issue 9, 2010, Pages 1381-1395

  Wang, Shuning ^a   Huang, Xiaolin ^a   Yam, Yeung ^b  

^a TSINGHUA UNIVERSITY   (China)

^b CHINESE UNIVERSITY OF HONG KONG   (Hong Kong)

Author keywords

Function approximation; hinging hyperplanes (HHs); neural networks; nonlinear identification; sigmoidal functions; smooth hinging hyperplanes (SHHs)

Indexed keywords

APPROXIMATION ERRORS; DIFFERENTIABILITY PROPERTIES; FUNCTION APPROXIMATION; FUNCTIONAL APPROXIMATION; GENERAL FUNCTIONS; HINGING HYPERPLANES; NON-DIFFERENTIABILITY; NONLINEAR IDENTIFICATIONS; OPTIMAL ERROR; SIGMOIDAL ACTIVATION FUNCTIONS; SIGMOIDAL FUNCTIONS; SIMULATION EXPERIMENTS; UPPER BOUND;

GEOMETRY;

NEURAL NETWORKS;

ALGORITHM; ARTICLE; ARTIFICIAL NEURAL NETWORK; BIOLOGICAL MODEL; NONLINEAR SYSTEM;

ALGORITHMS; MODELS, NEUROLOGICAL; NEURAL NETWORKS (COMPUTER); NONLINEAR DYNAMICS;

EID: 77956338893     PISSN: 10459227     EISSN: None     Source Type: Journal    
DOI: 10.1109/TNN.2010.2053383     Document Type: Article

References (21)

1. A. Barron, "Universal approximation bounds for superposition of a sigmoidal function," IEEE Trans. Inform. Theory, vol. 39, no. 3, pp. 930-945, May 1993.
2. L. Breiman, "Hinging hyperplanes for regression, classification, and function approximation," IEEE Trans. Inform. Theory, vol. 39, no. 3, pp. 999-1013, May 1993.
3. M. Burger and A. Neubauer, "Error bounds for approximation with neural networks," J. Approx. Theory, vol. 112, no. 2, pp. 235-250, Oct. 2001.
4. V. Cherkassky, D. Gehring, and F. Mulier, "Comparison of adaptive methods for function estimation from samples," IEEE Trans. Neural Netw., vol. 7, no. 4, pp. 969-984, Jul. 1996.
5. S. Ernst, "Hinging hyperplane trees for approximation and identification," in Proc. 37th IEEE Conf. Decision Control, Dec. 1998, pp. 1166- 1271.
6. A. M. Estudillo, F. M. Estudillo, C. H. Mart́nez, and N. G. Pedrajas, "Evolutionary product unit based neural networks for regression," Neural Netw., vol. 19, no. 4, pp. 477-486, 2006.
7. J. Gonźalez, I. Rojas, J. Ortega, H. Pomares, F. J. Ferńandez, and A. F. Díaz, "Multiobjective evolutionary optimization of the size, shape, and position parameters of radial basis function networks for function approximaztion," IEEE Trans. Neural Netw., vol. 14, no. 6, pp. 1478- 1495, Nov. 2003.
8. D. R. Hush and B. Horne, "Efficient algorithms for function approximation with piecewise linear sigmoidal networks," IEEE Trans. Neural Netw., vol. 9, no. 6, pp. 1129-1141, Nov. 1998.
9. P. Julían, M. Jord́an, and A. Desages, "Canonical piecewise-linear approximation of smooth functions," IEEE Trans. Circuits Syst. I, Fundam. Theory Appl., vol. 45, no. 5, pp. 567-571, May 1998.
10. V. Kurkov́a and M. Sanguineti, "Comparison of worst case errors in linear and neural network approximation," IEEE Trans. Inform. Theory, vol. 48, no. 1, pp. 264-275, Jan. 2002.
11. V. Kurkov́a and M. Sanguineti, "Geometric upper bounds on rates of variable-basis approximation," IEEE Trans. Inform. Theory, vol. 54, no. 12, pp. 5681-5688, Dec. 2008.
12. E. Lavretsky, "On the geometric convergence of neural approximations," IEEE Trans. Neural Netw., vol. 13, no. 2, pp. 273-282, Mar. 2002.
13. M. Ĺazaro, I. Santamaŕia, and C. Pantaléon, "A new EM-based training algorithm for RBF networks," Neural Netw., vol. 16, no. 1, pp. 69-77, 2003.
14. Y. Makovoz, "Random approximants and neural networks," J. Approx. Theory, vol. 85, no. 1, pp. 98-109, 1996.
15. O. Nelles, Nonlinear System Identification. Berlin, Germany: Springer- Verlag, 2001.
16. N. Plaziac, C. T. Ledinh, and J. P. Adoul, "PWL nonlinear adaptive filter via RLS and LMS algorithms," IEEE Trans. Signal Process., vol. 45, no. 5, pp. 1364-1367, May 1997.
17. P. Pucar and M. Millnert, "Smooth hinging hyperplanes: An alternative to neural nets," in Proc. 3rd Eur. Control Conf., Sep. 1995, pp. 1173- 1178.
18. P. Pucar and J. Sjöberg, "On the hinge-finding algorithm for hinging hyperplanes," IEEE Trans. Infor. Theory, vol. 44, no. 3, pp. 1310-1319, May 1998.
19. J. Roll, A. Bemporad, and L. Ljung, "Identification of piecewise affine systems via mixed-integer programming," Automatica, vol. 40, no. 1, pp. 37-50, 2004.
20. J. Sjöberg, Q. Zhang, and L. Ljung, "Nonlinear black-box modeling in system identification: A unified overview," Automatica, vol. 31, no. 12, pp. 1691-1724, 1995.
21. A. Súarez and J. F. Lutsko, "Globally optimal fuzzy decision trees for classification and regression," IEEE Trans. Pattern Anal. Mach. Intell., vol. 21, no. 12, pp. 1297-1311, Dec. 1999.