Data processing: artificial intelligence – Neural network – Structure
Patent
1994-11-02
1998-11-10
MacDonald, Allen R.
Data processing: artificial intelligence
Neural network
Structure
706 25, G06F 1518
Patent
active
058359028
ABSTRACT:
The present invention provides a system for learning from and responding to regularly arriving information at once by quickly combining prior information with concurrent trial information to produce useful learned information. At the beginning of each time trial a vector of measurement values and a vector of measurement plausibility values are supplied to the system, and a learning weight is either supplied to or generated by the system. The system then performs the following operations during each time trial: converting the measurement values to feature values; converting the measurement plausibility values to feature viability values; using each viability value to determine missing value status of each feature value; using non-missing feature values to update parameter learning; imputing each missing feature value from non-missing feature values and/or prior learning; converting imputed feature values to output imputed measurement values; and supplying a variety of feature value and feature function monitoring and interpretation statistics. A parallel embodiment of the system performs all such operations concurrently, through the coordinated use of parallel feature processors and a joint access memory, which contains connection weights and provision for connecting feature processors pairwise. The parallel version also performs feature function monitoring, interpretation and refinement operations promptly and in concert with concurrent operation, through the use of a parallel subsystem that receives interpretable concurrent connection weights from a parallel port. A nonparallel embodiment of the system uses a single processor to perform the above operations however, more slowly than the parallel embodiment, yet faster than available alternatives.
REFERENCES:
patent: 5148514 (1992-09-01), Arima
patent: 5157738 (1992-10-01), Carpenter
patent: 5214743 (1993-05-01), Asai
patent: 5222194 (1993-06-01), Nishimura
patent: 5253327 (1993-10-01), Yoshihara
patent: 5402522 (1995-03-01), Alkon
patent: 5408588 (1995-04-01), Ulug
patent: 5430830 (1995-07-01), Frank
patent: 5448684 (1995-09-01), Holt
patent: 5461696 (1995-10-01), Frank
patent: 5479575 (1995-12-01), Yoda
Chen, Design of Adaptive and Incremental Feed Forward Neural Networks, May 1993.
Bartczak, Towards Extending Adaptive Self Organizing Concurrent System Architechture, Dec. 1994.
Obradovic, Online train and recurrent neural networks with continuous topology adaptation, Jan. 1996.
A concurrent adaptive conjugate gradient learning algorithm on mimd shared memory access, Jul. 1993.
R.J. Jannarone, K.F. Yu, & Y. Takefuji, "Conjunctoids: Statistical Learning Modules for Binary Events," Neural Networks, vol. 1, pp. 325-337, 1988.
S. Mallya, & R.J. Jannarone, "Real-Time Pattern Recognition, I: Neural Network Algorithms for Normal Models," Proceedings of the Twenty-Third Symposium on System Theory, IEEE Computer Society Press, Los Alamitos, California, 1991, pp. 580-583.
Y. Hu, K. Ma, & R.J. Jannarone, "Real-Time Pattern Recognition, II: Visual Conjunctoid Neural Networks," Proceedings of the Twenty-Third Symposium on System Theory, IEEE Computer Society Press, Los Alamitos, California, 1991, pp. 584-589.
G. Tatman, & R.J. Jannarone, "Real-Time Pattern Recognition, III: Alternative Neural Networks for Speech Applications," Proceedings of the Twenty-Third Symposium on System Theory, IEEE Computer Society Press, Los Alamitos, California, 1991, 591-596.
P. Mehta, & R.J. Jannarone, "Real-Time Neural Networks: Conjunctoid Parallel Implementation," Proceedings of the Twenty-Third Symposium on System theory, IEEE Computer Society Press, Los Alamitos, California, 1991.
Y. Hu, "Automated Real-Time Neural Computing for Defense waste Processing," Proceedings of the International Topic Meeting on Nuclear and Hazardous Waste Management, American Nuclear Society, Inc., La Grange Park, IL, vol. 1, pp. 534-540, 1992.
Y. Takefuji, Neural Network Parallel Computing, Kluwer, Boston, 1992, Ch. 16.
R.J. Jannarone, "Concurrent Information Processing, I: An Applications Overview, " Applied Computing Review , vol. 1, 1-6, 1993.
A.D. Engineer, A Fast Kernal Algorithm for Concurrent Information Processing, Unpublished Masters Thesis, University of South Carolina, 1993.
K.V. Ananthakrishnan, A Concurrent Information Processing Coordinator Package, Unpublished Masters Thesis, University of South Carolina, 1993.
R.J. Jannarone, K. Ma, K.F. Yu, & J.W. Gorman, "Extended Conjunctoid Theory and Implementation: a General Model for Machine Cognition based on Categorical Data, "Progress in Neural Networks, vol. 3, Ablex, Norwood, NJ, pp. 361-425, 1994.
Y. Hu, Concurrent Information Processing with Pattern Recognition Applications, Unpublished Doctoral Dissertation, University of South Carolina, 1994.
R.J. Jannarone, K.F. Yu, and J.E. Laughlin, Easy Bayes Estimation for Rasch-Type Models, Psychometrika vol. 55, No. 3, 449-460, Sep. 1990.
MacDonald Allen R.
Smith Jeffrey S.
LandOfFree
Concurrent learning and performance information processing syste does not yet have a rating. At this time, there are no reviews or comments for this patent.
If you have personal experience with Concurrent learning and performance information processing syste, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Concurrent learning and performance information processing syste will most certainly appreciate the feedback.
Profile ID: LFUS-PAI-O-1528940