Patent
1991-06-17
1993-04-06
Fleming, Michael R.
395 24, G06F 1518
Patent
active
052010260
ABSTRACT:
To facilitate architecting of a multiple neural network, irrespective of the quantity of cases and the complexity of case dependence relationship, sets of input instances and the desirable outputs corresponding thereto are stored; the stored sets are read in sequence to discriminate whether all variables included in the input instances of the read set are included in the outputs of any given stored set, to mark variables not included in the outputs of any sets; the sets whose input instances include only the marked variables are selected from among the read sets; unit neural networks for learning the selected sets are formed and simultaneously variables included in the outputs of the formed unit neural networks are marked; a unit neural network for learning any given set is formed; and the formed unit neural networks are connected to each other to architect a multiple neural network.
REFERENCES:
patent: 5046019 (1991-09-01), Basehore
Anderson, "Data Representation in Neural Networks," AI Expert, Jun. 1990, pp. 30-37.
Josin, "Combinations of Neural Systems for Particular Situations," IEEE 1st International Conference on Neural Networks, Jun. 1987, pp. IV 517-524.
Stephen I. Gallant, "Connectionist Expert Systems", Communications of the ACM, Feb. 1988, vol. 31, No. 2, pp. 152-169.
Fleming Michael R.
Kabushiki Kaisha Toshiba
Tryon Jodi E.
LandOfFree
Method of architecting multiple neural network and system theref does not yet have a rating. At this time, there are no reviews or comments for this patent.
If you have personal experience with Method of architecting multiple neural network and system theref, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Method of architecting multiple neural network and system theref will most certainly appreciate the feedback.
Profile ID: LFUS-PAI-O-542553