
This Article  
 
Share  
Bibliographic References  
Add to:  
Digg Furl Spurl Blink Simpy Del.icio.us Y!MyWeb  
Search  
 
ASCII Text  x  
C.T. Lin, C.S.G. Lee, "NeuralNetworkBased Fuzzy Logic Control and Decision System," IEEE Transactions on Computers, vol. 40, no. 12, pp. 13201336, December, 1991.  
BibTex  x  
@article{ 10.1109/12.106218, author = {C.T. Lin and C.S.G. Lee}, title = {NeuralNetworkBased Fuzzy Logic Control and Decision System}, journal ={IEEE Transactions on Computers}, volume = {40}, number = {12}, issn = {00189340}, year = {1991}, pages = {13201336}, doi = {http://doi.ieeecomputersociety.org/10.1109/12.106218}, publisher = {IEEE Computer Society}, address = {Los Alamitos, CA, USA}, }  
RefWorks Procite/RefMan/Endnote  x  
TY  JOUR JO  IEEE Transactions on Computers TI  NeuralNetworkBased Fuzzy Logic Control and Decision System IS  12 SN  00189340 SP1320 EP1336 EPD  13201336 A1  C.T. Lin, A1  C.S.G. Lee, PY  1991 KW  neural network based fuzzy logic control; connectionist model; decision system; feedforward multilayer net; learning; backpropagation; inference engine; performance; artificial intelligence; decision theory; fuzzy logic; inference mechanisms; learning systems; neural nets. VL  40 JA  IEEE Transactions on Computers ER   
A general neuralnetwork (connectionist) model for fuzzy logic control and decision systems is proposed. This connectionist model, in the form of feedforward multilayer net, combines the idea of fuzzy logic controller and neuralnetwork structure and learning abilities into an integrated neuralnetworkbased fuzzy logic control and decision system. A fuzzy logic control decision network is constructed automatically by learning the training examples itself. By combining both unsupervised (selforganized) and supervised learning schemes, the learning speed converges much faster than the original backpropagation learning algorithm. The connectionist structure avoids the rulematching time of the inference engine in the traditional fuzzy logic system. Two examples are presented to illustrate the performance and applicability of the proposed model.
[1] L.A. Zadeh, "Fuzzy sets,"Inform. Contr., vol. 8, pp. 338353, 1965.
[2] M. Sugeno, Ed.,Industrial Applications of Fuzzy Control. Amsterdam: NorthHolland, 1985.
[3] C. C. Lee, "Fuzzy logic in control systems: Fuzzy logic controllerPart I&II,"IEEE Trans. Syst., Man, Cybern., vol. SMC20, no. 2, pp. 404435, 1990.
[4] L. A. Zadeh, "Fuzzy logic,"IEEE Comput. Mag., pp. 8393, Apr. 1988.
[5] K. L. Self, "Fuzzy logic design,"IEEE Spectrum, vol. 27, pp. 4244 and 105, Nov. 1990.
[6] Y. F. Li and C. C. Lan, "Development of fuzzy algorithms for servo systems,"IEEE Contr. Syst. Mag., pp. 6572, Apr. 1989.
[7] E. M. Scharf and N. J. Mandic, "The application of a fuzzy controller to the control of a multidegreefreedom robot arm," inIndustrial Application of Fuzzy Control, M. Sugeno, Ed. Amsterdam: NorthHolland, 1985, pp. 4162.
[8] S. Shao, "Fuzzy selforganizing controller and its application for dynamic processes,"Fuzzy Sets Syst., vol. 26, pp. 151164, 1988.
[9] R. Tanscheit and E. M. Scharf, "Experiments with the use of a rulebased selforganizing controller for robotics applications,"Fuzzy Sets Syst., vol. 26, pp. 195214, 1988.
[10] M. Sugeno and M. Nishida, "Fuzzy control of model car,"Fuzzy Sets Syst., vol. 16, pp. 103113, 1985.
[11] T. Sejnowski and C. Rosenberg, "NETtalk: A parallel network that learns to read aloud," JHU/EECS86/01, Tech. Rep., EECS Dep., Johns Hopkins Univ., 1986.
[12] K. Fukushima, S. Miyaka, and T. Ito, "Neocognitron: A neural network model for a mechanism of visual pattern recognition,"IEEE Trans. Syst., Man, Cybern., vol. SMC13, no. 5, pp. 826834, 1983.
[13] S. Grossberg, "Cortical dynamics of threedimensional form, color, and brightness perceptions,"Perception and Psychophys., vol. 41, no. 2, pp. 87116, 1987.
[14] A. G. Barto, R.S. Sutton, and C. W. Anderson, "Neuronlike adaptive elements that can solve difficult learning control problems,"IEEE Trans. Syst., Man, Cybern., vol. SMC13, no. 5, pp. 834847, 1983.
[15] C. W. Anderson, "Learning to control an inverted pendulum using neural network,"IEEE Contr. Syst. Mag., pp. 3136, Apr. 1989.
[16] F. C. Chen, "Backpropagation neural network for nonlinear selftuning adaptive control,"Proc. IEEE Intelligent Machine, pp. 274279, 1989.
[17] G. E. Hinton, J. L. McClelland, and D. E. Rumelhart, "Distributed representations," inParallel Distributed Processing, Vol. 1. Cambridge, MA: M.I.T. Press, 1986, pp. 77109.
[18] G. E. Hinton, "Connectionist learning procedures,"Artif. Intell., vol. 40, no. 1, pp. 143150, 1989.
[19] B. Kosko, "Unsupervised learning in noise,"IEEE Trans. Neural Networks, vol. 1, no. 1, pp. 4457, 1990.
[20] A. Amano and T. Aritsuka, "On the use of neural networks and fuzzy logic in speech recognition," inProc. 1989 Int. Joint Conf. Neural Networks, 1989, pp. 301305.
[21] C. C. Lee and H. R. Berenji, "An intelligent controller based on approximate reasoning and reinforcement learning,"Proc. IEEE Intelligent Machine, pp. 200205, 1989.
[22] B. Kosko, "Adaptive inference in fuzzy knowledge networks," inProc. 1987 Int. Joint Conf. Neural Networks, 1987, pp. II 261268.
[23] D. E. Rumelhart, G. E. Hinton, and R. J. Williams, "Learning internal representation by error propagation,"Parallel Distributed Processing: Explorations in the Microstructure of Cognition, vols. 1 and 2. Cambridge, MA: MIT Press, 1986.
[24] J. Moody and C. J. Darken, "Fast learning in networks of locallytuned processing units,"Neural Computat., vol. 1, pp. 281294, 1989.
[25] W. Y. Huang and R. P. Lippmann, "Neural net and traditional classifiers," inNeural Information Processing Systems. New York: American Institute of Physics, 1988, pp. 387396.
[26] M. Braae and D. A. Rutherford, "Fuzzy relations in a control setting,"Kybernetes, vol. 7, no. 3, pp. 185188, 1978.
[27] M. Togai and H. Watanabe, "Expert system on a chip: An engine for realtime approximate reasoning,"IEEE Expert Syst. Mag., vol. 1, pp. 5562, 1986.
[28] T. Yamakawa and T. Miki, "The current mode fuzzy logic integrated circuits fabricated by the standard CMOS process,"IEEE Trans. Comput., vol. C35, no. 2, pp. 161167, 1986.
[29] D. S. Touretzky and G. E. Hinton, "A distributed connectionist production system," CMUCS86172, Tech. Rep., Dep. Comput. Sci., Carnegie Mellon Univ., 1986.
[30] S. I. Gallant, "Connectionist expert systems,"Commun. ACM, vol. 31, no. 2, pp. 152169, Feb. 1988.
[31] T. Kohonen,SelfOrganization and Associative Memory. Berlin, Germany: SpringerVerlag, 1988, p. 132.
[32] D. E. Rumelhart and D. Zipser, "Feature discovery by competitive learning,"Cognitive Sci., vol. 9, pp. 75112, 1985.
[33] S. Grossberg, "Adaptive pattern classification and universal recoding, I: Parallel development and coding of neural feature detectors,"Biol. Cybern., vol. 23, pp. 121134, 1976.
[34] T. E. Vollmann, W. L. Berry, and D. C. Whybark,Manufacturing Planning and Control Systems. Homewood, IL: Richard D. Irwin, Inc., 1988, ch. 13.
[35] K. R. Baker,Introduction to Sequencing and Scheduling. New York: Wiley, 1974.
[36] H. W. Sorenson and D. L. Alspach, "Recursive Bayesian estimation using Gaussian sums,"Automatica, vol. 7, no. 4, pp. 465479, July 1971.
[37] S. Lee and R. M. Kil, "Multilayer feedforward potential function network," inProc. 1988 Int. Joint Conf. Neural Networks, 1988, pp. 11611171.
[38] J. A. Franklin, "Input space representation for refinement learning control," inProc. 1989 Int. Symp. Intelligent Contr., 1989, pp. 115122.
[39] S. J. Hanson and L. Y. Pratt, "Comparing biases for minimal network construction with backpropagation, " inAdvances in Neural Information Processing Systems 1. Los Altos, CA: Morgan Kaufmann, 1989, pp. 177185.
[40] S. Amari, "Neural theory of association and conceptformation,"Biol. Cybern., vol. 26, pp. 175185, 1977.