Predictive network with learned preprocessing parameters

Details Predictive network with learned preprocessing parameters Predictive network with learned preprocessing parameters

1999-06-11

2000-11-07

Dorvil, Richemond

Data processing: artificial intelligence

Neural network

Learning task

706 23, 706 22, G06F 1518

Patent

active

061449520

ABSTRACT:
A predictive network is disclosed for operating in a runtime mode and in a training mode. The network includes a preprocessor (34') for preprocessing input data in accordance with parameters stored in a storage device (14') for output as preprocessed data to a delay device (36'). The delay device (36') provides a predetermined amount of delay as defined by predetermined delay settings in a storage device (18). The delayed data is input to a system model (26') which is operable in a training mode or a runtime mode. In the training mode, training data is stored in a data file (10) and retrieved therefrom for preprocessing and delay and then input to the system model (26'). Model parameters are learned and then stored in the storage device (22). During the training mode, the preprocess parameters are defined and stored in a storage device (14) in a particular sequence and delay settings are determined in the storage device (18). During the runtime mode, runtime data is derived from a distributed control system (24) and then preprocessed in accordance with predetermined process parameters and delayed in accordance with the predetermined delay settings. The preprocessed data is then input to the system model (26') to provide a predicted output, which is a control output to the distributed control system (24).

REFERENCES:
patent: 5140523 (1992-08-01), Frankel et al.
patent: 5150313 (1992-09-01), Engh et al.
patent: 5175797 (1992-12-01), Funabashi et al.
patent: 5255347 (1993-10-01), Matsuba et al.
patent: 5335291 (1994-08-01), Kramer et al.
patent: 5479573 (1995-12-01), Keeler et al.
W. H. Press, "Numerical Recipes," Cambridge University Press (1986), pp. 77-101.
"Predicting the Future: Advantages of Semilocal Units" by Eric Hartman and James D. Keeler, Neural Computation 3, pp. 556-578 (1991).
"How Neural Nets Work" by Alan Lapedes and Robert Farber, American Institute of Physics, pp. 442-456 (1988).
"Predicting the Future: A Connectionist Approach" by Andreas S. Weigend, Bernardo A. Huberman and David E. Rumelhart, Stanford-PDP-90-01/PARC-SSL-90-20 (Apr. 1990).
"Learning Internal Representations by Error Propagation" by D. E. Rumelhart, G. E. Hinton and R. J. Williams, Parallel Distributed Processing, vol. 1, 1986.
"Integrating Time Alignment and Neural Networks for High Performance Continuous Speech Recognition," by Patrick Haffner, Michael Franzini and Alex Waibel, ICASSP 91, sponsored by The Institute of Electrical and Electronics Engineers, Signal Processing Signal, 1991 International Conference on Acoustics, Speech and Signal Processing, May 14-17, 1991, pp. 105-108.
"A Model for Temporal Correlation of Biological Neuronal Spike Trains," David C. Tam and the late Donald H. Perkel, IJCNN International Joint Conference of Neural Networks, Department of Physiology and Biophysics, University of California, Irvine, CA 92717, pp. 1-781 -1-786.
Neural Network Architecture for Adaptive System Modeling and Control by Esther Levin, Raanan Gewirtzman and Gideon F. Inbar, Neural Networks, pp. 185-191, 1991.
"Towards Practical Control Design Neural Computation" by T. Troudel, S. Garg, D. Mattern and W. Merrill, ICJNN-91-Seattle--International Joint Conference on Neural Networks, vol. 2, pp. 675-681, Jul. 8, 1991.
"Pulse-Processing Neural Net Hardware with Selectable Topology and Adaptive Weights and Delays" by J. R. Beerhold, M. Jansen and R. Eckmiller, IJCNN International Joint Conference on Neural Networks, vol. 2, pp. 569-574, Jun. 17, 1990.
"Learning the Time-Delay Characteristics in a Neural Network" by P. W. Rander and K. P. Unnikrishnan, ICASSP-92--IEEE International Conference on Acoustics, Speech and Signal Processing, vol. 2, pp. 285-288, Mar. 23, 1992.

Affiliated with

Also associated with

Rating

Predictive network with learned preprocessing parameters does not yet have a rating. At this time, there are no reviews or comments for this patent.

If you have personal experience with Predictive network with learned preprocessing parameters, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Predictive network with learned preprocessing parameters will most certainly appreciate the feedback.

Rate now

Comments { 0 }

Profile ID: LFUS-PAI-O-1651594