Patent
1993-09-30
1995-10-03
MacDonald, Allen R.
395 11, 395 21, 395 50, 395 52, G06F 1518
Patent
active
054558905
ABSTRACT:
Neural networks learn expert system rules, for either business or real-time applications, to improve the robustness and speed of execution of the expert system. One or more neural networks are constructed which incorporate the production rules of one or more expert systems. Each neural network is constructed of neurons or neuron circuits each having only one significant processing element in the form of a multiplier. Each neural network utilizes a training algorithm which does not require repetitive training and which yields a global minimum to each given set of input vectors.
REFERENCES:
patent: 5121467 (1992-06-01), Skeirik
patent: 5129037 (1992-07-01), Kirk et al.
patent: 5255344 (1993-10-01), Takagi et al.
patent: 5263120 (1993-11-01), Bickel
Hruska et al, "hybrid learning in expert networks"; International Joint Conference on Neural Networks, pp. 117-120 vol. 2, 8-14 Jul. 1991.
Hsu et al. "imprecise reasoning using neural networks", Proceedings of the Twenty-Third Annual Hawaii International Conference on System and Sciences, pp. 363-368 vol. 4, 2-5 Jan. 1990.
Hayashi et al, "fuzzy neural network with fuzzy signals and weights", International Joint Conference on Neural Networks, pp. 696-701 vol. 2, 7-11 Jun. 1992.
Hafiz Tariq
MacDonald Allen R.
Motorola Inc.
Nielsen Walter W.
Stuckman Bruce E.
LandOfFree
Method for structuring an expert system utilizing one or more ne 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 for structuring an expert system utilizing one or more ne, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Method for structuring an expert system utilizing one or more ne will most certainly appreciate the feedback.
Profile ID: LFUS-PAI-O-1082618