Robustness quantification of recurrent neural network using unscented transform

Neurocomputing

Volumn 74, Issue 1-3, 2010, Pages 354-361

  Wang, Xiaoyu ^a   Huang, Yong ^a   Nguyen, Nhan ^b  

^a AMRL   (United States)

^b NASA AMES RESEARCH CENTER   (United States)

Author keywords

Recurrent neural network; Robustness; Uncertainty propagation; Unscented transform

Indexed keywords

MODELING CAPABILITIES; NETWORK FAULTS; PARAMETRIC UNCERTAINTIES; PERFORMANCE LOSS; ROBUSTNESS; ROBUSTNESS MEASURES; SENSITIVITY MATRIX; UNCERTAINTY PROPAGATION; UNSCENTED TRANSFORM;

DYNAMICAL SYSTEMS; NONLINEAR DYNAMICAL SYSTEMS; RECURRENT NEURAL NETWORKS;

UNCERTAINTY ANALYSIS;

ARTICLE; ARTIFICIAL NEURAL NETWORK; INTERMETHOD COMPARISON; PRIORITY JOURNAL; QUANTITATIVE ANALYSIS; UNCERTAINTY;

EID: 78649486392     PISSN: 09252312     EISSN: None     Source Type: Journal    
DOI: 10.1016/j.neucom.2010.03.010     Document Type: Article

References (30)

1. Haykin S. Neural Networks: A Comprehensive Foundation 1999, Prentice-Hall, Upper Saddle River, NJ. second ed.
2. C. Chiu, K. Mehrotra, et al., Robustness of feedforward neural networks, in: Proceedings of the IEEE International Conference on Neural Networks, vol. 2, 1993, pp. 783-788.
3. C. Alippi, M. Milena, A poly-time analysis of robustness in feedforward neural networks, in: Proceedings of the IEEE International Workshop on Virtual and Intelligent Measurement Systmes, Budapest, Hungary, May 19-20, vol. 1, 2001, pp. 76-80.
4. C. Alippi, D. Sam, et al., A training-time analysis of robustness in feed-forward neural networks, in: Proceedings of the IEEE International Joint Conference on Neural Networks, vol. 4, 2004, pp. 2853-2858.
5. Dundar G., Rose K. The effects of quantization on multilayer neural networks. IEEE Transactions on Neural Networks 1995, 6(6):1446-1451.
6. Razavi B. Design of Analog CMOS Integrated Circuits 2000, McGraw-Hill, New York.
7. Widrow B., Kolla' r J. Quantization Noise 2002, Prentice-Hall, New Jersey, USA.
8. Eickhoff R., Ruckert U. Robustness of radial basis functions. Neurocomputing 2007, 70:2758-2767.
9. A. Assoum, M. Geagea, et al., Influence on ANNs fault tolerance of binary errors introduced during training, in: Proceedings of the International Conference on Information and Communication Technologies: From Theory to Applications, 2004, pp. 435-436.
10. Phatak D.S., Koren I. Complete and partial fault tolerance of feedforward neural nets. IEEE Transactions on Neural Networks 1995, 6(2):446-456.
11. Pierce S.G., Haim Y.B., et al. Evaluation of neural network robust reliability using information-gap theory. IEEE Transactions on Neural Networks 2006, 17(6):1349-1361.
12. D. Liu, A.N. Michel, Robustness analysis of a class of neural networks, in: Circuits and Systems, Proceedings of the 36th Midwest Symposium, 1993, pp. 1077-1080.
13. Liu D., Michel A.N. Robustness analysis and design of a class of neural networks with sparse interconnecting structure. Neurocomputing 1996, 12:59-76.
14. Feng Z., Michel A.N. Robustness analysis of a class of discrete-time recurrent neural networks under perturbations. IEEE Transactions on Circuits and Systems-I: Fundamental Theory and Applications 1999, 46:1482-1486.
15. S.O. Yee, M.Y. Chow, Robustness of an induction motor incipient fault detector neural network subject to small input perturbations, in: IEEE Proceedings of Southeastcon '91, vol. 1, 1991, pp. 365-369.
16. KrishnaKumar K., Nishta K. Robustness analysis of neural networks with an application to system identification. Journal of Guidance, Control and Dynamics 1999, 22:695-701.
17. Loh W.L. On Latin hypercube sampling. Annals of Statistics 1996, 24(5):2058-2080.
18. Swidzinski J.F., Kai C. Nonlinear statistical modeling and yield estimation technique for use in Monte Carlo simulations. IEEE Transactions on Microwave Theory and Techniques 2000, 48(12):2316-2324.
19. Wan E.A., Merwe R.V.D. Kalman Filtering and Neural Networks. The Unscented Kalman Filter 2001, Wiley Publishing, (Chapter 7). S. Haykin (Ed.).
20. Horn R.A., Johnson C.R. Matrix Analysis 1990, Cambridge University Press.
21. Kwak N. Principal component analysis based on L1-Norm maximization. IEEE Transactions on Pattern Analysis and Machine Intelligence 2008, 30(9):1672-1680.
22. Wang X., Huang Y. Optimized recurrent neural network-based tool wear modeling in hard turning. Transactions of NAMRI/SME 2009, 37:213-220.
23. Wang X., Wang W., et al. Design of neural network-based estimator for tool wear modeling in hard turning. Journal of Intelligent Manufacturing 2008, 19(4):383-396.
24. Werbos P.J. Back propagation through time: what it does and how to do it. Proceedings of the IEEE 1990, 78(10):1550-1560.
25. S. Singhal, L. Wu, Training feed forward networks with extended Kalman filter algorithm, in: Proceedings of the ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing, Glasgow, Scotland, 23-26 May, 1989, pp. 1187-1190.
26. Zhang L. Neural network-based market clearing price prediction and confidence interval estimation with an improved extended Kalman filter method. IEEE Transactions on Power Systems 2005, 20(1):59-66.
27. Puskorius G.V., Feldkamp L.A. Neurocontrol of nonlinear dynamical systems with Kalman filter trained recurrent networks. IEEE Transactions on Neural Networks 1994, 5:279-297.
28. KrishnaKumar K. Optimization of the neural net connectivity pattern using a backpropagation algorithm. Neurocomputing 1993, 5:273-286.
29. Narendra K.S. Adaptive Control of Dynamical System Using Neural Networks, Handbook of Intelligent Control Neural, Fuzzy, and Adaptive Approaches 1992, Van Nostrand Reinhold, New York, NY.
30. Baksalary J.K., Kala R. A new bound for the euclidean norm of the difference between the least squares and the best linear unbiased estimators. The Annals of Statistics 1980, 3:679-681.