Robustness of radial basis functions

Neurocomputing

Volumn 70, Issue 16-18, 2007, Pages 2758-2767

  Eickhoff, Ralf ^a   Rückert, Ulrich ^a  

^a UNIVERSITY OF PADERBORN   (Germany)

Author keywords

Equicontinuity; Nanoelectronics; Radial basis function; Robustness; Sensitivity analysis

Indexed keywords

MEAN SQUARE ERROR; NANOELECTRONICS; NEURAL NETWORKS; NEURONS; ROBUSTNESS (CONTROL SYSTEMS); SENSITIVITY ANALYSIS;

EQUICONTINUITY; NOISE CONTAMINATED PARAMETERS;

RADIAL BASIS FUNCTION NETWORKS;

ALGORITHM; ANALYTICAL ERROR; ANALYTICAL PARAMETERS; ARTICLE; ARTIFICIAL NEURAL NETWORK; CONTROLLED STUDY; LINEAR SYSTEM; MATHEMATICAL COMPUTING; MOLECULAR ELECTRONICS; NONLINEAR SYSTEM; NORMAL DISTRIBUTION; PRIORITY JOURNAL; QUANTITATIVE ANALYSIS; RADIAL BASED FUNCTION; RELIABILITY; SENSITIVITY ANALYSIS; SIGNAL NOISE RATIO; SUPPORT VECTOR MACHINE;

EID: 34548182842     PISSN: 09252312     EISSN: None     Source Type: Journal    
DOI: 10.1016/j.neucom.2006.04.012     Document Type: Article

References (40)

1. Arbib M.A. The Handbook of Brain Theory and Neural Networks. second ed. (2002), MIT Press, Cambridge, MA, USA
2. Bauer Jr. K.W., Alsing S.G., and Greene K.A. Feature screening using signal-to-noise ratios. Neurocomputing 31 1-4 (2000) 29-44
3. V. Beiu, U. Rückert, S. Roy, J. Nyathi, On nanoelectronic architectural challenges and solutions, in: Proceedings of IEEE Conference on Nanotechnology IEEE NANO 2004, Munich, Germany, 17-19 August 2005, IEEE.
4. Bilotti A., and Mariani E. Noise characteristics of current mirror sinks/sources. IEEE J. Solid-State Circuits 10 6 (1975) 516-524
5. G.R. Bolt, Investigating fault tolerance in artificial neural networks, Technical Report YCS 154, Computer Science Department, University of York, UK, March 1991.
6. Bronstein I.N., and Semendyayev K.A. Handbook of Mathematics. third ed. (1997), Springer, Berlin
7. Chandra P., and Singh Y. Feedforward sigmoidal networks-equicontinuity and fault-tolerance properties. IEEE Trans. Neural Networks 15 6 (2004) 1350-1366
8. Cherry E.C. Some experiments on the recognition of speech, with one and two ears. J. Acoust. Soc. Am. 25 (1953) 975-979
9. Cun Y.L., Denker J.S., and Solla S.A. Optimal brain damage. In: Touretzky D.S. (Ed). Advances in Neural Information Processing Systems: Proceedings of the 1989 Conference (1990), San Mateo, CA, Morgan Kaufmann, Los Altos, CA 598-605
10. Du S., Chen Z., Yuan Z., and Zhang X. Sensitivity to noise in bidirectional associative memory (bam). IEEE Trans. Neural Networks 16 4 (2005) 887-898
11. R. Eickhoff, U. Rückert, Tolerance of radial-basis functions against stuck-at-faults, in: Proceedings of the International Conference on Artificial Neural Networks (ICANN), Warsaw, Poland, 11-15 September 2005, Lecture Notes in Computer Science, vol. 3697, Springer, Berlin, pp. 1003-1008.
12. Geva S., and Sitte J. A constructive method for multivariate function approximation by multilayer perceptrons. IEEE Trans. Neural Networks 3 4 (1992) 621-624
13. Girosi F., Jones M., and Poggio T. Regularization theory and neural networks architectures. Neural Comput. 7 2 (1995) 219-269
14. Girosi F., and Poggio T. Networks and the best approximation property. Biol. Cybern. 63 (1990) 169-176
15. Guggenbuhl W., Di J., and Goette J. Switched-current memory circuits for high-precision applications. IEEE J. Solid-State Circuits 29 9 (1994) 1108-1116
16. Haykin S. Neural Networks, A Comprehensive Foundation. second ed. (1999), Prentice-Hall, Englewood Cliffs, NJ, USA
17. Haykin S., and Chen Z. The cocktail party problem. Neural Comput. 17 9 (2005) 1875-1902
18. Huang G.-B., Saratchandran P., and Sundararajan N. A generalized growing and pruning rbf (ggap-rbf) neural network for function approximation. IEEE Trans. Neural Networks 16 1 (2005) 57-67
19. Larsson P. di/dt noise in cmos integrated circuits. Analog Integrated Circuits Signal Process. 14 1-2 (1997) 113-129
20. MacGregor R.J. Neural Modeling: Electrical Signal Processing in the Nervous System (1977), Plenum Press, New York
21. X. Parra, A. Català, Sensitive analysis of radial basis function networks for fault tolerance purposes, in: Fifth International Work-Conference on Artificial Neural Networks (IWANN), vol. 1, Alicante, Spain, 1999, pp. 566-572.
22. X. Parra, A. Català, Learning fault tolerance in radial basis function networks, in: M. Verleysen (Ed.), Proceedings of the Ninth European Symposium on Artificial Neural Networks (ESANN), Bruges, Belgium, April 2001, D-Side Publications, pp. 341-346.
23. Patterson D.A., and Hennessy J.L. Computer Organization and Design (1998), Morgan Kaufmann, San Francisco
24. Pernia-Espinoza A.V., Ordieres-Mere J.B., Martinez-de Pison F.J., and Gonzalez-Marcos A. Tao-robust backpropagation learning algorithm. Neural Networks 18 2 (2005) 191-204
25. Phatak D.S., and Koren I. Complete and partial fault tolerance of feedforward neural nets. IEEE Trans. Neural Networks 6 2 (1995) 446-456
26. Razavi B. Design of Analog CMOS Integrated Circuits (2000), McGraw-Hill, New York
27. U. Rückert, H. Surmann, Tolerance of a binary associative memory towards stuck-at-faults, in: T. Kohonen (Ed.), Artificial Neural Networks, vol. 2, North-Holland, Amsterdam, 1991, pp. 1195-1198.
28. Rudin W. Principles of Mathematical Analysis, International Series in Pure and Applied Mathematics (1976), McGraw-Hill, New York
29. C.E. Shannon, A mathematical theory of communication, Bell Syst. Tech. J. 27 (1948) 379-423; 623-656.
30. Shen D., and Cruz Jr. J.B. Encoding strategy for maximum noise tolerance bidirectional associative memory. IEEE Trans. Neural Networks 16 2 (2005) 293-300
31. Simmons G.F. Topology and Modern Analysis (1964), McGraw-Hill, Tokyo, Japan
32. Sitte J., Körner T., and Rückert U. Local cluster neural net: analog VLSI design. Neurocomputing 19 (1998) 185-197
33. Sze S.M. High Speed Semiconductor Devices (1990), Wiley, New York
34. Tanenbaum A.S. Structured Computer Organization. fourth ed. (1999), Prentice-Hall, Englewood Cliffs, NJ
35. Tchernev E.B., Mulvaney R.G., and Phatak D.S. Investigating the fault tolerance of neural networks. Neural Comput. 17 7 (2005) 1646-1664
36. Tchernev E.B., Mulvaney R.G., and Phatak D.S. Perfect fault tolerance of the n-k-n network. Neural Comput. 17 9 (2005) 1911-1920
37. Tsividis Y. Operation and Modeling of the MOS Transistor (1987), McGraw-Hill, New York, NY, USA
38. Vapnik V.N. Statistical Learning Theory (1998), Wiley-Interscience, New York
39. Verikas A., and Bacauskiene M. Feature selection with neural networks. Pattern Recognition Lett. 23 11 (2002) 1323-1335
40. Widrow B., and Kollár J. Quantization Noise (2002), Prentice-Hall, NJ, USA