Data processing: artificial intelligence – Neural network – Learning method
Patent
1997-09-23
1999-11-16
Hafiz, Tariq R.
Data processing: artificial intelligence
Neural network
Learning method
706 14, 706 15, 706 23, G06E 100, G06E 300
Patent
active
059874449
ABSTRACT:
A robust neural system for robust processing is disclosed for averting unacceptable or disastrous processing performances. This robust neural system either comprises a neural network or comprises a neural network and at least one range transformer. At least one adjustable weight of the robust neural system is a nonlinear weight of the neural work determined in a nonadaptive training of the robust neural system with respect to a nonadaptive risk-sensitive training criterion.
If all the adjustable weights of the robust neural system are nonadaptively adjustable, all these weights are held fixed during the robust neural system's operation. If said neural network is recursive, and the nonadaptive training data used to construct said nonadaptive risk-sensitive training criterion contain data for each of a number of typical values of an environmental parameter, the robust neural system is not only robust but also adaptive to the environmental parameter.
If the robust neural system comprises both nonadaptively and adaptively adjustable weights, these adaptively adjustable weights are adjusted by an adaptor in the robust neural system during its operation. Such a robust neural system is called a robust adaptive neural system. Two types of adaptor are described.
REFERENCES:
patent: 5003490 (1991-03-01), Castelaz et al.
patent: 5150323 (1992-09-01), Castelaz
patent: 5408424 (1995-04-01), Lo
patent: 5649065 (1997-07-01), Lo et al.
patent: 5748847 (1998-05-01), Lo
K. Narendra and K. Parthasarathy, "Identification and Control of Dynamical System Using Neural Networks," IEEE Transactions on Neural Networks, vol. 1, No. 1, pp. 4-27 (1990).
G. Puskorius and L. Feldcamp, "Neurocontrol of Nonlinear Dynamical Systems with Kalman Filter Trained Recurrent Networks," IEEE Trainsactions on Neural Networks, vol. 5, No. 2, pp. 279-297 (1994).
O. Nerrand et al, "Neural Networks and Nonlinear Adaptive Filtering: Unifying Concepts and New Algorithms," Neural Computation, vol. 5, pp. 165-199 (1993).
L. Yin et al, "A New Class of Nonlinear Filters--Neural Filters," IEEE Transaction on Signal Processing, vol. 41, pp. 1201-1222 (1993).
B. Hassibi and T. Kailath, "H-infinity Optimal Training Algorithms and their Relation to Backpropagation," Advances in Neural Information Processing Systems, vol. 7, pp. 191-199, MIT Press (1995).
J. Connor, R. Martin and L Atlas, "Recurrent Neural Networks and Robust Time Series Prediction," IEEE Trainsactions on Neural Networks, vol. 3, No. 2, pp. 240-254 (1994).
B. Hassibi, A. Sayed and T. Kailath, "H-infinity Optimality of the LMS Algorithm," IEEE Trainsactions on Signal Processing, vol. 44, No. 2, pp. 267-280 (1996).
B. Hassibi, A. Sayed and T. Kailath, "Linear Estimation in Krein Spaces--Part I: Theory," IEEE Trainsactions on Automatic Control, vol. 41, No. 1, pp. 18-33 (1996).
B. Hassibi, A. Sayed and T. Kailath, "Linear Estimation in Krein Spaces--Part II: Applications," IEEE Trainsactions on Automatic Control, vol. 41, No. 1, pp. 34-49 (1996).
J. Speyer, C. Fan and R. Banavar, "Optimal Stochastic Estimation with Exponential Cost Criteria," Proceedings of the 31st Conference on Decision and Control, pp. 2293-2298 (1992).
M. James, J. Baras and R. Ellicott, "Risk-Sensitive Control and Dynamic Games for Partially Observed Discrete-time Nonlinear Systems," IEEE Trainsactions on Automatic Control, vol. 39, No. 4, pp. 780-792 (1996).
J. Baras and N. Patel, "Information State for Robust Control of Set-Valued Discrete Time Systems," Proceedings of the 34th Conference on Decision and Control, pp. 2302-2307 (1995).
W. Lin and C. Byrnes, "H-infinity-Control of Discrete-Time Nonlinear Systems," IEEE Trainsactions on Automatic Control, vol. 41, No. 4, pp. 494-510 (1996).
A. Bensoussan and R. Ellicott, "General Finite-Dimensional Risk-Sensitive Problems and Small Noise Limits," IEEE Trainsactions on Automatic Control, vol. 41, No. 2, pp. 210-215 (1996).
J. Lo, "Risk-Sensitive Approximation of Functions by Neural Networks," Proceedings of the 34th Allerton Conference on Communication, Control, and Computing, Monticello, Illinois, pp. 991-996 (1996).
J. Lo, "Risk-Sensitive Identification of Dynamic Systems by Neural Networks," Proceedings of the 34th Allerton Conference on Communication, Controlk, and Computing, Monticello, Illinois, pp. 982-990 (1996).
J. Lo, "Model Reference Risk-Sensitive Neurocontrol for a Deterministic Plant," Proceedings of the 31st Annual Conference on Information Sciences and Systems, Johns Hopkins U., Balti., pp. 441-446 (1997).
J. Lo, "Robust Adaptive Identification of Dynamic Systems by Neural Networks," Proceedings of the 1997 International Conference on Neural Networks, vol. 2, pp. 1121-1126 (1997).
J. Lo, "Robust Adaptive Neurofilters with or without On-Line Weight Adjustment," Proceedings of the 1997 International Conference on Neural Networks, vol. 4, pp. 2245-2250 (1997).
Song, Q., Robust Training Algorithm for a Perceptron Neuron., Neural Networks, Jan. 1997., International Conference on vol.: 3, pp.: 1907-1912 vol. 3.
Larsen, J., et al., Design of Robust Neural Network Classifiers, Acoustics, Speech, and Signal Processing, Jan. 1998., Proceedings of the 1998 IEEE Conference on vol.: 2, pp.: 1205-1208 vol. 2.
Joonsuk Kim; Seo, J.H., Implementation of a robust feedforward neural network using the classifier structure, Neural Networks, Jan. 1994. IEEE World Congress on Computational Intelligence., 1994 IEEE International Conference on vol.: 3 , pp.: 1427-1432.
Sean Meyn, "Call for Papers: Thirty-Fourth Annual Allerton Conference on Communication, Control, and Computing", URL: <http://www.cds.caltech.edu/extras/conferences/ALLER96/> (viewed on: May 4, 1999; 0927HRS).
Leahy, M.B., Jr., et al., Robust Model-Based Neural Network Control, Systems Engineering, Jan. 1990., IEEE International Conference on, pp.: 343-346.
Shuzhi Sam Ge, Robust Adaptive NN Feedback Linearization Control of Nonlinear Systems, Intelligent Control, 1996 IEEE International Symposium on, pp.: 486-491, Jan. 1996.
Rovithakis, G.A., et Al., A Robust Direct Adaptive Regulation Architecture Using Dynamic Neural Network Models., Systems, Man, and Cybernetics, Jan. 1994. Humans, Information and Technology., 1994 IEEE International Conference on vol.: 2, pp. 1110-1115 vo.
Hafiz Tariq R.
Starks, Jr. Wilbert L.
LandOfFree
Robust neutral systems does not yet have a rating. At this time, there are no reviews or comments for this patent.
If you have personal experience with Robust neutral systems, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Robust neutral systems will most certainly appreciate the feedback.
Profile ID: LFUS-PAI-O-1337435