Boots – shoes – and leggings
Patent
1993-05-28
1995-04-18
Mai, Tan V.
Boots, shoes, and leggings
395 23, G06F 1531, G06F 1546
Patent
active
054084245
ABSTRACT:
A method and an apparatus are disclosed for processing a measurement process to estimate a signal process. The method synthesizes realizations of a signal process and a measurement process into a primary filter for estimating the signal process and, if required, an ancillary filter for providing the primary filter's estimation error statistics. Both the primary and the ancillary filters are made out of artificial recurrent neural networks (RNNs). Their implementation results in the filtering apparatus. The synthesis is performed through training RNNs. The weights/parameters and initial dynamic state of an RNN are determined by minimizing a training criterion by the variation of the same. The training criterion, which is constructed on the basis of a selected estimation error criterion, incorporates the aforementioned realizations. An alternative way to determine the initial dynamic state of an RNN is to simply set it equal to a canonical initial dynamic state. After adequate training, both the primary and the ancillary filters are recursive filters optimal for the given respective RNN architectures with the lagged feedbacks carrying the optimal conditional statistics. If appropriate RNN paradigms and estimation error criteria are selected, the primary and the ancillary filters of such paradigms are proven to approximate the respective optimal filters in performance (with respect to the selected estimation error criteria) to any desired degree of accuracy, provided that the RNNs that constitute the primary and ancillary filters are of sufficient sizes.
REFERENCES:
patent: 4947482 (1990-08-01), Brown
patent: 4979124 (1990-12-01), Sachse et al.
patent: 5003490 (1991-03-01), Castelaz et al.
patent: 5056037 (1991-10-01), Eberhardt
patent: 5099434 (1992-03-01), Stoll et al.
patent: 5129039 (1992-07-01), Hiraiwa
patent: 5150323 (1992-09-01), Castelaz
patent: 5182794 (1993-01-01), Gasperi et al.
R. S. Bucy and K. D. Senne, "Digital Synthesis of Non-linear Filters", Automatica, vol. 7, pp. 287-298 (1971).
R. S. Bucy and K. D. Senne, "Non-linear Filtering Algorithms for Vector Processing Machines", Comp. & Maths. with Apps., vol. 6, pp. 317-338 (1980).
J. T.-H. Lo, "Optimal Estimation for the Satellite Attitude Using Star Tracker Measurements", Automatica, vol. 22, pp. 477-482 (1986).
J. T.-H. Lo and S.-K. Ng, "Optimal Fourirer-Hermite Expansion for Estimation", Stochastic Processes and their Applications, vol. 21, pp. 291-304 (1986).
S. I. Sudharsanan and M. K. Sundareshan, "Maximum A posteriori State Estimation: A Neural Processing Algorithm", in Procs. of the 28th Conf. on Decision and Control, Tampa, Fla., pp. 1805-1806 (1989).
Q. Sun et al., "A Neural Network Computation Algorithm for Discrete-Time Linear System State Estimation", in Procs. of IJCNN, Jun. 1992, Baltimore, Md., p. I-443 (1992).
J. L. Elman, "Finding Structure in Time", Cognitive Science, vol. 14, pp. 179-211 (1990).
D. L. Elliott, "A Better Activation Function for Artificial Neural Networks", ISR Technical Report TR-93-8, Institute for Systems Research, University of Maryland, College Park, Md. 20742 (1993).
M. I. Jordan, "Attractor Dynamics and Parallelism in a Connectionist Sequential Machine", in Procs. of the 8th Annual Conf. of the Cognitive Science Society, pp. 531-546, Erlbaum (1986).
J. T.-H. Lo, "Finite-dimensional Sensor Orbits and Optimal Nonlinear Filtering", IEEE Transactions on Information Theory, vol. IT-18, pp. 583-588 (1972).
K. Hornik et al., "Multilayer Feedforward Networks are Universal Approximators", Neural Networks, vol. 2, pp. 359-366 (1989).
P. Poddar and K. P. Unnikrishnan, "Non-linear Prediction of Speech Signals Using Memory Neuron Networks", in Neural Networks for Signal Processing, ed. J. H. Juang et al., pp. 395-404 (1991).
A. J. Robinson and F. Fallside, "A Dynamic Connectionist Model for Phoneme Recognition", in Neural Networks from Models to Applications, ed. L. Personnaz and G. Dreyfus, pp. 541-550, IDEST, Paris (1989).
O. Nerrand et al, "Neural Network Training Schemes for Non-linear Adaptive Filtering and Modelling", in Procs. of IJCNN, Jun. 1991, Seattle, Wash., pp. I-61-I-66 (1991).
J. P. DeCruyenaere and H. M. Hafez, "A Comparison between Kalman Filters and Recurrent Neural Networks", in Procs. of IJCNN, Jun. 1992, Baltimore, Md., pp. IV-247-IV-251 (1992).
J. T.-H. Lo, "Optical Filtering by Recurrent Neural Networks", in Procs. of the 30th Annual Allerton Conf. on Comm., Contr., and Comput., Monticello, Ill., Oct. 1992, ed. P. Van Dooren and M. Spong, pp. 903-912 (1992).
J. T.-H. Lo, "Synthetic Approach to Optimal Filtering", Procs. of the 1992 Intl. Simul. Tech. Conf. and 1992 Workshop on Neural Networks, Clear Lake, Tex., Nov. 1992, pp. 475-481 (1992).
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).
LandOfFree
Optimal filtering by recurrent neural networks does not yet have a rating. At this time, there are no reviews or comments for this patent.
If you have personal experience with Optimal filtering by recurrent neural networks, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Optimal filtering by recurrent neural networks will most certainly appreciate the feedback.
Profile ID: LFUS-PAI-O-70972