A Low-Sensitivity Recurrent Neural Network

Neural Computation

Volumn 10, Issue 1, 1998, Pages 165-188

  Back, Andrew D ^a   Tsoi, Ah Chung ^b  

^a INST OF PHYS AND CHEMICAL RESEARCH   (Japan)

^b UNIVERSITY OF WOLLONGONG   (Australia)

Author keywords

[No Author keywords available]

Indexed keywords

EID: 0346966878     PISSN: 08997667     EISSN: None     Source Type: Journal    
DOI: 10.1162/089976698300017935     Document Type: Article

References (38)

1. Agarwal, R., & Burrus, C. (1975). New recursive digital filter structures having very low sensitivity and roundoff noise. IEEE Trans. Circuits, Syst., CAS-22(12), 921-927.
2. Alippi, C., Piuri, V., & Sami, M. (1995). Sensitivity to errors in artificial neural networks: A behavioral approach. IEEE Trans. Circuits, Syst. I: Fundamental Theory and Applications, 42(6), 358-361.
3. Astrom, K., Hagander, P., & Sternby, J. (1984). Zeros of sampled systems. Automatica, 20(1), 31-38.
4. Back, A. D, & Tsoi, A.-C. (1994). A comparison of discrete-time operator models for nonlinear system identification. In D. S. T. G. Tesauro & T. K. Leen (Eds.), Advances in neural information processing systems 7 (pp. 883-890). Cambridge, MA: MIT Press.
5. Back, A. D., & Tsoi, A.-C. (1995). Constrained pole-zero filters as discrete-time operators for system approximation. In E. M. F. Girosi, J. Makhoul, & E. Wilson (Eds.), Proc. of the 1995 IEEE Workshop Neural Networks for Signal Processing 5 (NNSP95) (pp. 191-200). New York: IEEE Press.
6. Back, A. D, Wan, E., Lawrence, S., & Tsoi, A.-C. (1994). A unifying view of some training algorithms for multilayer perceptrons with FIR filter synapses. In J. H. J. Vlontzos & E. Wilson (Eds.), Proc. of the 1994 IEEE Workshop Neural Networks for Signal Processing 4 (NNSP94) (pp. 146-154). New York: IEEE Press.
7. Choi, J., & Choi, C.-H. (1992). Sensitivity analysis of multilayer perceptrons with differentiable activation functions. IEEE Trans. Neural Networks, 3, 101-107.
8. Dahlquist, G., & Bjorck, A. (1974). Numerical methods. Englewood Cliffs, NJ: Prentice Hall.
9. de Vries, B., & Principe, J. (1992). The Gamma model - a new neural model for temporal processing. Neural Networks, 5(4), 565-576.
10. Dündar, G., & Rose, K. (1995). The effects of quantization on multilayer perceptrons. IEEE Trans. Neural Networks, 6(6), 1446-1451.
11. Fan, H., & Li, Q. (1993). A δ-operator recursive gradient algorithm for adaptive signal processing. In Proc. IEEE Int. Conf. Acoust. Speech, Signal Proc. (Vol. III, pp. 492-495). New York: IEEE Press.
12. Gevers, M., & Li, G. (1993). Parameterizations in control, estimation and filtering problems: Accuracy aspects. London: Springer-Verlag.
13. Gold, B., & Radar, C. (1969). Digital processing of signals. New York: McGraw-Hill.
14. Goodwin, G., Middleton, R., & Poor, H. (1992). High-speed digital signal processing and control. Proc. IEEE, 80(2), 240-259.
15. Heuberger, P., Bosgra, O., & Van den Hof, P. (1995). A generalized orthonormal basis for linear dynamical systems. IEEE Trans. Automat. Control, AC-40(3), 451-165.
16. Kerlirzin, P. & Réfrégier, P. (1995). Theoretical investigation of the robustness of multilayer perceptrons: Analysis of the linear case and extension to nonlinear networks. IEEE Trans. Neural Networks, 6, 560-571.
17. Mantey, P. (1968). Eigenvalue sensitivity and state-variable selection. IEEE Trans. Automat. Control, AC-13(3), 263-269.
18. Mhaskar, H. (1996). Neural networks and approximation theory. Neural Networks, 9(4), 721-722.
19. Middleton, R., & Goodwin, G. (1990). Digital control and estimation. Englewood Cliffs, NJ: Prentice-Hall.
20. Minai, A., & Williams, R. (1994). Perturbation response in feedforward networks. Neural Networks, 7(5), 783-796.
21. Oh, S.-H., & Lee, Y. (1995). Sensitivity analysis of single hidden-layer neural networks with threshold functions. IEEE Trans. Neural Networks, 6, 1005-1007.
22. Orlandi, G., & Martinelli, G. (1984). Low-sensitivity recursive digital filters obtained via the delay replacement. IEEE Trans. Circuits, Syst., CAS-31, 654-657.
23. Orzechowski, N., Kumara, S., & Das, C. (1993). Performance of multilayer neural networks in binary-to-binary mappings under weight errors. In Proc. ICNN93, San Francisco (pp. 1684-1689). New York: IEEE Press.
24. Palaniswami, M. (1989). A new discrete-time operator for digital estimation and control (Tech. Rep. No. 1). University of Melbourne, Department of Electrical Engineering.
25. Principe, J., de Vries, B., & de Oliveira, P. G. (1993). The Gamma filter - a new class of adaptive IIR filters with restricted feedback. IEEE Trans. Signal Processing, 41, 649-656.
26. Puskorius, G. V., & Feldkamp, L. A. (1992). Model reference adaptive control with recurrent networks trained by the dynamic DEKF algorithm. In Proceedings of the 1992 International Joint Conference on Neural Networks, Baltimore, Maryland.
27. Rabiner, L., & Gold, B. (1975). Theory and application of digital signal processing. Englewood Cliffs, NJ: Prentice Hall.
28. Roberts, R., & Mullis, C. (1987). Digital signal processing. Reading, MA: Addison-Wesley.
29. Robinson, A. (1989). Dynamic error propagation networks. Unpublished doctoral dissertation, Cambridge University.
30. Stevenson, M., Winter, R., & Widrow, B. (1990). Sensitivity analysis of feedforward neural networks to weight errors. IEEE Trans. Neural Networks, 1, 71-90.
31. Vidyasagar, M. (1978). Nonlinear systems analysis. Englewood Cliffs, NJ: Prentice Hall.
32. Von Lehman, A., Paek, E., Liao, P., Marrakchi, A., & Patel, J. (1989). Influence of interconnection weight discretization and noise in an optoelectronic neural network. Optics Letters, 14, 928-930.
33. Wahlberg, B. (1991). System identification using Laguerre models. IEEE Trans. Automat. Control, 36, 551-562.
34. Wang, K., & Michel, A. (1994). Robustness and perturbation analysis of a class of artificial neural networks. Neural Networks, 7(2), 251-259.
35. Williams, R., & Zipser, D. (1989). A learning algorithm for continually running fully recurrent neural networks. Neural Computation, 1, 270-280.
36. Williamson, D. (1988). Delay replacement in direct form structures. IEEE Trans. Acoust., Speech, Signal Processing, 34(4), 453-460.
37. Wray, J., & Green, G. (1994). Calculation of the Volterra kernels of non-linear dynamic sytems using an artificial neural network. Biological Cybernetics, 71, 187-195.
38. Xie, Y., & Jabri, M. (1992). Analysis of the effects of quantization in multilayer neural networks using a statistical model. IEEE Trans. Neural Networks, 3, 334-338.