1994-03-04
1996-06-04
Davis, George B.
395 61, 395 3, G06F 1518
Patent
active
055241760
ABSTRACT:
In the present invention, prior art techniques are extended to allow application of the backpropagation learning technique to artificial neural networks derived from fuzzy expert system rule-bases. A method in accordance with the invention, referred to herein as a Fuzzy Expert Network (FEN), is implemented in a programmed machine such as a computer to provide automated learning of both "fine" and "coarse" knowledge in a network of artificial neural objects (ANOs) implementing fuzzy modeling rules. Through application of the FEN method, an event-driven fuzzy expert network comprising acyclically connected ANOs derived from fuzzy modelling rules may be implemented. Neural objects implement one or more fuzzy combining and defuzzification rules and use backpropagation of error techniques to implement learning. As in prior art, the FEN allows each ANO to adjust its input weight parameters--"fine" knowledge learning. Unlike prior art, the FEN allows each ANO to modify its internal parameters--"coarse" knowledge learning. This latter action means that individual ANOs have the capability to modify the parameters of the fuzzy rule's membership function upon which they are based. In this way the FEN is able to change the structure of its encoded knowledge over time, making it a more adaptable architecture for autonomous and/or adaptable control systems. Simulation results showing the FEN's learning and adaptability behavior are given.
REFERENCES:
patent: 4326259 (1982-04-01), Cooper et al.
patent: 4593367 (1986-06-01), Slack et al.
patent: 4912647 (1990-03-01), Wood
patent: 4912649 (1990-03-01), Wood
patent: 4912651 (1990-03-01), Wood et al.
patent: 4912652 (1990-03-01), Wood
patent: 4912653 (1990-03-01), Wood et al.
patent: 4912654 (1990-03-01), Wood
patent: 4912655 (1990-03-01), Wood
patent: 4914603 (1990-04-01), Wood
patent: 4979126 (1990-12-01), Pao et al.
patent: 5168549 (1992-12-01), Takagi et al.
patent: 5175797 (1992-12-01), Funabashi et al.
patent: 5255344 (1993-10-01), Takagi et al.
Specht et al., "Probabalistic Neural Networks for Classification, Mapping, or Associative Memory", IEEE Inter. Conf. on Neural Networks, Jul. 1988.
Keller, "Fuzzy Logic Inference Neural Networks", SPIE vol. 1192 Intelligent Robots and Computer Vision VIII, 1989.
Hayashi et al., "Systems Engineering Applications of Fuzzy Neural Networks", IJCNN, 7-11 Jun. 1992.
Hayashi, et al., "Fuzzy Neural Network with Fuzzy Signals and Weights" IJCNN, 7-11 Jun. 1992.
Enbutsu et al., "Fuzzy Rule Extraction from a Multilayered Neural Network", IJCNN, 8-14, Jul. 1991.
Horikawa et al., "On Fuzzy Modeling Using Fuzzy Neural Networks with the Back-Propagation Algorithm", IEEE Trans-On Neural Networks, Sep. 1992.
Sun, "Rule-Base Structure Identification in an Adaptive-Network-Based Fuzzy Interference System" IEEE Trans-On Fuzzy Systems, Feb. 1994.
Eshera, "Parallel Rule-Based Fuzzy Interference on Mesh-Connected Systolic Arrays" IEEE Expert, 1989.
K. Narita and R. C. Lacher, "FEN (Fuzzy Expert Networks) learning architecture," Proceeding of the 1993 International Joint Conference on Neural Networks, vol. II, pp. 1901-1905, Oct. 1993.
Chester, Lamb, and Dhurjati, Rule-Based Computer Alarm Analysis in Chemical Process Plants, Proceedings of 7th Annual Micro-Delcon '84, Mar. 1994, pp. 22-29.
Fu, Integration of Neural Heuristics into Knowledge-Based Inference, Connection Science, 1990.
Li Min Fu, Rule Learning by Searching on Adapted NETS, Proceedings of American Association of Artificial Intelligence Conference, 1991, pp. 590-595.
Hirota, K. and Pedrycz, W., Fuzzy Logic Neural Networks: Design and Computations, 1991 IEEE International Joint Conference on Neural Networks, vol. 1, 1991, pp. 152-175.
Kaihara, Koyama, Minamikawa, and Yasaka, A Rule-Based Physicians' Consultation System for Cardiovascular Disease, Proceedings of the International Conference on Cybernetics and Society, 1978, pp. 85-88.
Kuncicky, The Transmission of Knowledge Between Neural Networks and Expert Systems, Proceedings of the [First] Workshop on Neural Networks: Academic/Industrial/NASA/Defense, 1990, pp. 311-319.
Lacher, Hruska, and Kuncicky, Backpropagation Learning in Expert Networks, FSUCS Tech. 1991 Report 91-915, pp. 1-24.
Lacher, Hruska, Kuncicky, Back-Propagation Learning in Expert Networks, IEEE Transactions on Neural Networks, vol. 3, No. 1, 1992.
Lacher, Chapter 2: Node Error Assignment in Expert Networks, Intelligent Hybrid Systems, A. Kandel and G. Langholz, Eds. Boca Raton, FL., CRC Press.
Rumelhaart and McClelland, Parallel Distributed Processing vol. 1, Cambridge, MA, MIT Press, 1986, pp. 444-459.
Lacher, Hruska and Kuncicky, Expert Networks: A Neural Network Connection to Symbolic Reasoning Systems, Proceedings of the Fourth Florida Artificial Intelligence Research Symposium, Apr. 2-5, 1991, pp. 12-16.
Lacher, Hruska, Kuncicky, Expert Networks: A Neural Network Connection to Symbolic Reasoning Systems FSUCS Technical Report 90-092, Sep., 1990, pp. 1-28.
Kuncicky, Hruska, and R. C. Lacher, Hybrid Systems: The Equivalence of Rule-Based Expert System and Artificial Network Inference, Department of Computer Science, Florida State University, pp. 1-24.
Hruska, Kuncicky, and Lacher, Learning in Acyclic Neural Networks, FSUCS Technical Report 90-052, May 1990, pp. 1-4.
Hruska, Kuncicky, and Lacher Learning in Acyclic Expert Networks, Proceedings of the Second workshop on Neural Networks: Academic/Industrial/NASA/Defense, Feb. 11-13, 1991, vol. 1515, pp. 181-184.
Schwartz and Kir, Fuzzy Logic Flowers in Japan, IEEE Spectrum, Jul. 1992, pp. 32-35.
Munakata and Jani, Fuzzy Systems: An Overview, Communications of the ACM, Mar. 1994, vol. 37, No. 3, pp. 70-76.
Zadeh, Fuzzy Logic, Neural Networks, and Soft Computing, Communications of the ACM, Mar. 1994, vol. 37, No. 3, pp. 77-84.
Lacher Robert C.
Narita Kazunari
Daido Steel Co. Ltd.
Davis George B.
The Florida State University
LandOfFree
Fuzzy expert system learning 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 Fuzzy expert system learning network, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Fuzzy expert system learning network will most certainly appreciate the feedback.
Profile ID: LFUS-PAI-O-391429