Data processing: artificial intelligence – Neural network – Learning method
Patent
1997-07-09
2000-06-27
Hafiz, Tariq R.
Data processing: artificial intelligence
Neural network
Learning method
706 21, 704240, G06E 100
Patent
active
060817976
ABSTRACT:
The present invention comprises an adaptive temporal correlation network (ATCN) that correlates data patterns, or events, over time. More specifically, the ATCN comprises a plurality of time slices wherein each time slice represents one or more data streams that have occurred at the same time. The ATCN assigns each data stream to a module in the time slice. The ATCN analyzes each data stream and identifies and classifies a data pattern/event found within the data stream. Once an event is found, the ATCN flags that event as active within the module and creates temporal connections between the active event and all other events within the network. The present invention also has a prediction phase in which the probability of the occurrence of future events is predicted. When predicting the occurrence of future events, the ATCN receiving an event, locates that event within the network, and traverses the temporal connections of that event to identify other events in the current time slice and other time slices that are most likely to occur.
REFERENCES:
patent: 5040214 (1991-08-01), Grossberg et al.
patent: 5479573 (1995-12-01), Keeler et al.
patent: 5515490 (1996-05-01), Buchanan et al.
I. Kirschning et al., Phoneme Recognition Using a Time-Sliced Recurrent Recognizer, Jul. 1994 IEEE International Conference on Neural Networks, vol. 7, pp. 4437-4441.
F. Zhong et al., An NN-Based Dynamic Time-Slice Scheme for Bandwidth Allocation in ATM Networks, Proceedings of Sep. 1997 International Conference on Information, Communications and Signal Processing, 1997, vol. 1, pp. 345-350.
B.W. Stiles et al., A Habituation Based Neural Network for Spatio-Temporal Classification, Proceedings of the Sep. 1995 IEEE Workshop on Neural Networks for Signal Processing[1995]V, pp. 135-144.
American Heuristics Corporation, http://micky.heuristics.com/, Mar. 18, 1999, 11:22 AM.
M. Paolini, http://phaistos.uscd.edu/.about.paolini/revcorr-diagram.html/, Mar. 18, 1999, 11:34 AM.
American Heuristics Corporation
Hafiz Tariq R.
Starks, Jr. Wilbert L.
LandOfFree
Adaptive temporal correlation network does not yet have a rating. At this time, there are no reviews or comments for this patent.
If you have personal experience with Adaptive temporal correlation network, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Adaptive temporal correlation network will most certainly appreciate the feedback.
Profile ID: LFUS-PAI-O-1792669