1996-03-25
1998-04-14
Hafiz, Tariq R.
395 3, 395 61, 395900, 395 21, 395 23, 395 24, G06F 1500, G06F 1518, G06G 700
Patent
active
057403228
ABSTRACT:
A fuzzy neural network system includes a learning function. The learning is performed by determining degrees of coincidence of rules from combinations of membership functions for realizing fuzzy rules, constructing a network based on the number of input and output items, in such a manner as to produce output in conformity with the degrees of coincidence, to thereby properly simulate relations between input and output as to sample data represented by a subject input pattern and an output pattern corresponding thereto. The system further includes a fuzzy rule setup portion for programming fuzzy rules created by engineers into the fuzzy neural network, a fuzzy rule extracting portion for extracting each fuzzy rule from the network after a learning period, and a degree-of-importance extracting portion which extracts, for each input, a respective contribution ratio of each input on each output in the network, after a learning period. In a preferred embodiment, the network structure includes an input layer, a membership layer having front and rear halves, a rule layer, and an output layer.
REFERENCES:
patent: 5524176 (1996-06-01), Narita et al.
Okada et al. "Initializing Multilayer Neural Networks with Fuzzy Logic," Proceedings of the 1992 International Joint Conference on Neural Networks (IJCNN), vol. 1, pp. 239-244, Jun. 1992.
Sulzberger et al. "FUN: Optimization of Fuzzy Rule Based Systems Using Neural Networks," Neural Networks, 1993 International Conference, pp. 312-316, 1993.
Kawamura et al., "Neurofuzzy System--An Overview and a Prototype System," in Participating Symposium to IIASA: Recent Developments and the Latest Applications of Neurofuzzy System, Nov. 1992, pp. 180-187.
Okada, et al., Initializing Multilayer Neural Networks with Fuzzy Logic, 1992, vol. 1, pp. 188-193.
Horikawa, et al., On Fuzzy Modeling Using Neural Networks with the Back-Propagation Algorithm, 1992, vol. 3, pp. 801-806.
English-language abstract of JP 4-092901, Uchikawa.
English-language abstract of JP 5-073323, Asogawa.
English-language abstract of JP 5-224939, Kawamura.
English-language abstract of JP 6-119175, Kawamura.
English-language abstract of JP 6-161761, Kawamura.
Conlin, Esq. David G.
Hafiz Tariq R.
Rhodes Jason W.
Sharp Kabushiki Kaisha
LandOfFree
Fuzzy-neural network system does not yet have a rating. At this time, there are no reviews or comments for this patent.
If you have personal experience with Fuzzy-neural network system, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Fuzzy-neural network system will most certainly appreciate the feedback.
Profile ID: LFUS-PAI-O-644974