Simplified neural networks algorithm for function approximation on discrete input spaces in high dimension-limited sample applications

Neurocomputing

Volumn 72, Issue 4-6, 2009, Pages 1078-1083

  Haider, Syed Shabbir ^a   Zeng, Xiao Jun ^a  

^a UNIVERSITY OF MANCHESTER   (United Kingdom)

Author keywords

Discrete input spaces; Function approximation; Neural networks; Simplified NN architecture; Universal approximation

Indexed keywords

APPROXIMATING FUNCTIONS; APPROXIMATION ACCURACIES; DATA SETS; DISCRETE INPUT SPACES; FEEDFORWARD; FUNCTION APPROXIMATION; HIDDEN LAYERS; HIGH DIMENSIONS; LINEAR FUNCTIONS; NEURAL NETWORK ARCHITECTURES; NEURAL NETWORKS ALGORITHMS; SIMPLIFIED NN ARCHITECTURE; UNIVERSAL APPROXIMATION;

APPROXIMATION ALGORITHMS; ELECTROMAGNETIC WAVE EMISSION; FEEDFORWARD NEURAL NETWORKS; FUNCTIONS; LEARNING ALGORITHMS; LEARNING SYSTEMS; METROPOLITAN AREA NETWORKS; MULTILAYER NEURAL NETWORKS; MULTILAYERS; POLYNOMIAL APPROXIMATION; PROBABILITY DENSITY FUNCTION; VEGETATION;

NEURAL NETWORKS;

ALGORITHM; ARTICLE; ARTIFICIAL NEURAL NETWORK; LEARNING; MATHEMATICAL COMPUTING; POSITIVE FEEDBACK; PRIORITY JOURNAL; SIMULATION;

EID: 58149461174     PISSN: 09252312     EISSN: None     Source Type: Journal    
DOI: 10.1016/j.neucom.2008.03.011     Document Type: Article

References (20)

1. Allan Pinkus. Approximation theory of MLP model in neural networks. Acta Numer. 8 (1999) 143-195
2. H. Altay Guvenir, I. Uysal, Bilkent University Function Approximation Repository, 〈http://funapp.cs.bilkent.edu.tr〉, 2000.
3. Basheer I.A., and Hajmeer M. Artificial neural networks: fundamentals, computing, design, and application. J. Microbiol. Methods 43 (2000) 3-31
4. Cybenko G. Approximation by superpositions of sigmoidal function. Math. Control Signals Syst. 2 (1989) 303-314
5. Franco Scarselli, and Chung Tsoi A.H. Universal approximation using feedforward neural networks: a survey of some existing methods, and some new results. Neural Netw. 11 1 (1998) 15-37
6. Hagan M., Demuth H., and De Jesus O. An introduction to the use of neural networks in control systems. Int. J. Robust Nonlinear Control 12 11 (2002) 959-985
7. Hornik K., Stinchcombe M., and White H. Multilayer feedforward networks are universal approximators. Neural Netw. 2 (1989) 359-366
8. Huang G.-B., and Chen L. Convex incremental extreme learning machine. Neurocomputing 70 16-18 (2007) 3056-3062
9. Huang G.-B., Chen L., and Siew C.-K. Universal approximation using incremental constructive feedforward networks with random hidden nodes. IEEE Trans. Neural Netw. 17 4 (2006) 879-892
10. Huang G.-B., Zhu Q.-Y., and Siew C.-K. Extreme learning machine: theory and applications. Neurocomputing 70 (2006) 489-501
11. Jeff Schneider Andrew Moore. Active Learning in Discrete Input Spaces. Proceedings of the 34th Interface Symposium (2002)
12. Leshno M., Lin V.Y., Pinkus A., and Schocken S. Multilayer feedforward networks with a nonpolynomial activation function can approximate any function. Neural Netw. 6 6 (1993) 861-867
13. Mhaskar H.N., and Nahmwoo Hahm. Neural networks for function approximation and system identification. Neural Comput. 9 (1997) 143-159
14. Poggio T., and Girosi F. A theory of networks for approximation and learning, networks for approximation and learning. Proc. IEEE (Special Issue Neural Netw. 78 9 (1990) 1481-1497
15. Ratsko R., Selmic A., and Lewis F.L. Neural network approximation of piecewise continuous functions: application to friction compensation. IEEE Trans. Neural Netw. 13 3 (2002) 745-751
16. Silvia Ferrari, and Stengel R.F. Smooth function approximation using neural networks. IEEE Trans. Neural Netw. 16 1 (2005) 24-38
17. Stinchcombe M.B. Neural network approximation of continuous functionals and continuous functionals on compactifications. Neural Netw. 12 (1999) 467-477
18. Tikk D., Kóczy L.T., and Gedeon T.D. A survey on the universal approximation and its limits in soft computing techniques. Int. J. Approximate Reasoning 33 2 (2003) 185-202
19. Zeng X.-J., Goulerma J.Y., Keane J.A., and Liatsis P. Approximation capabilities of hierarchical neural-fuzzy systems for function approximation on discrete spaces. Int. J. comput. Intell. Res. 1 1 (2005) 29-41
20. Zeng X.-J., John, and Keane A. Approximation capabilities of hierarchical fuzzy systems. IEEE Transa. Fuzzy Syst. 13 5 (2005) 659-672