Abstract
In this paper the authors present a novel classification of the diverse architectures for intelligent systems. The authors discuss the classification with particular reference to the current uninhabited areas that offer potential for future research. The authors then describe how their work on neurofuzzy systems fits into this model. The paper provides an overview of the proposed neurofuzzy architecture for approximate fuzzy reasoning. The term approximate fuzzy reasoning is employed to highlight an approximation to the conventional fuzzy reasoning approach which considerably simplifies the resulting architecture. The performance of the approach is demonstrated by its application to benchmark problems. Simulation results are presented using the Matlab neural network toolbox and these are compared with traditional neural networks; other fuzzy neural networks and conventional fuzzy reasoning approaches. The work demonstrates the advantage of a neurofuzzy approach and highlights the advantages of this architecture for a hardware realisation.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
References
Afzalian, A., Linkens, D.A., 2000. “Training of neurofuzzy power system stabilisers using genetic algorithms”. Jour of Electrical Power & Energy Systems, Vol. 22, no. 2, pp. 93–102.
Alimi, A.M., 1997. “An evolutionary neuro-fuzzy approach to recognize on-line Arabic handwriting”, IEEE Proc. of the 4th Int. Conf. on Document Analysis and Recognition, Vol.1, pp. 382–386.
Blake, J.J., Maguire, L.P., McGinnity, T.M., 1998. “The Implementation Of Fuzzy Systems, Neural Networks and Fuzzy Neural Networks Using FPGAs”, Information Sciences, Vol. 112, no. 1–4, pp. 151–68.
Brown, M. and Harris, C., 1994. “Neurofuzzy adaptive modelling and control”, Prentice-Hall.
Gupta, M. M. and Rao, D.H., 1994. “On the principles of fuzzy neural networks”, Proc. Fuzzy Sets and Systems, pp. 1–18, vol. 61.
Higuchi, T. et al. 1999. “Real-world applications of analog and digital evolvable hardware”, IEEE Transactions on Evolutionary Computation, Vol. 3 no. 3, pp. 220–235.
Horikawa, S., Furuhashi, T. and Uchikawa, Y., 1992. “On fuzzy modelling using fuzzy neural networks with the back propagation algorithm”, IEEE Neural Nets, pp. 801–806, Vol 3, no. 5.
Ichimura, T., Tazaki, E., 1995. “Applying adaptive structured genetic algorithm to reasoning and learning method for fuzzy rules using neural networks”. 1995 IEEE Int. Conf. on Neural Networks, Part 6, pp. 3124–3128.
Jang, Roger J. S. and Sun, C.-T., 1995. “Neuro-fuzzy modelling and Control” Proc. of the IEEE, pp. 378–406, vol. 83, no 3 March.
Kasabov, N., 1998. “Evolving fuzzy neural networks, theory and applications for on-line adaptive prediction, decision making and control”. Australian Journal of Intelligent Information Processing Systems, Vol.5, no. 3, pp. 154–160.
Lin, C.T., Lee, C.S.G., 1994. “Reinforcement structure/ parameter learning for neural-network-based fuzzy logic control systems”, IEEE Trans. Fuzzy Systems, pp. 46–63, Vol. 2, no. 1.
Maguire, L.P., McGinnity, T.M. and McDaid, L.J., 1997. “A Fuzzy Neural Network for Approximate Fuzzy Reasoning” Chapter in “Hybrid Intelligent Systems. Fuzzy Logic, Neural networks and Genetic Algorithms” Da Ruan (Ed), Kluwer Academic Publisher, pp. 35–58.
Mange, D, Stauffer, A, Tempesti, G., 1998. “Embryonics. a macroscopic view of the cellular architecture”, Evolvable Systems. From Biology to Hardware ICES 98, pp 174–184.
Mange, D. et al., 1998. “Embryonics. a new methodology for designing field-programmable gate arrays with self-repair and self-replicating properties”, IEEE Transactions on VLSI Systems, Vol. 6 no. 3, pp 387–99.
McGinnity, T.M., Roche, B., L.P., Maguire, L.J., McDaid, 1998. “Novel Architectures and Synapse Design for Hardware Implementation of Neural Networks”, Int. Journal Computers and Electrical Engineering, Pergamon, V24, no 1/2, pp. 75–88.
Mitra S., Pal, S.K., 1994. “Logical operation based fuzzy MLP for classification and rule generation”. Neural Networks, pp. 353–373, vol. 7, no 2.
Nie, J., Linkens, D., 1992. “Neural network-based approximate reasoning principles and implementation”. Int. Journal of Control, pp. 399–413, vol. 56, no. 2.
Ortega, C, Tyrrell, A., 1998. “Evolvable hardware for fault-tolerant applications”, lEE Colloquium Evolvable Hardware Systems, pp 4/1–5.
Russo, F., 1999. “Evolutionary neural fuzzy systems for noise cancellation in image data”. IEEE Transactions on Instrumentation & Measurement, Vol. 48, no. 5, pp. 915–920.
Simpson, P.K., Jahns, G., 1993. “Fuzzy min-max neural networks for function approximation”. Proc. IEEE Int. Conf. on Neural Networks, pp. 1967–1972, vol. 3.
Sipper, M., Mange, D., Sanchez, E., 1999. “Quo vadis evolvable hardware?”. Communications of the ACM, Vol.42 no. 4,, pp 50–8, Apr.
Stoica, A., 1999. “Toward evolvable hardware chips. Experiments with a programmable transistor array”. Proc. IEEE Microneuro99, IEEE Comput. Soc. pp. 156–162.
Takagi, H., 1990. “Fusion Technology of Fuzzy Theory and Neural Networks. Survey and Future Directions”, Proc. Int. Conf. on Fuzzy Logic and Neural Networks, pp. 13–26.
Takagi, T, Hayashi, I., 1991. “NN-Driven fuzzy reasoning”. Int Jour of Approx Reasoning, pp 191–212. Vol 5.
Takagi, T, Sugeno, M., 1985. “Fuzzy identification of Systems and its application to modelling and control” IEEE Trans. Systems Man and Cybernetics, Vol 15, pp. 116–132.
Thompson, A., Layzell, P., 1999. “Analysis of unconventional evolved electronics”. Communications of the ACM, Vol. 42 no. 4, pp 71–9.
Yao, X., 1999. “Evolving artificial neural networks”, Proc. of the IEEE, Vol. 87, no. 9, pp. 1423–1447
Author information
Authors and Affiliations
Editor information
Rights and permissions
Copyright information
© 2002 Springer Science+Business Media New York
About this chapter
Cite this chapter
Maguire, L.P., McGinnity, T.M., Glackin, B.P. (2002). Hybrid Intelligent Architectures using a Neurofuzzy Approach. In: Zimmermann, HJ., Tselentis, G., van Someren, M., Dounias, G. (eds) Advances in Computational Intelligence and Learning. International Series in Intelligent Technologies, vol 18. Springer, Dordrecht. https://doi.org/10.1007/978-94-010-0324-7_10
Download citation
DOI: https://doi.org/10.1007/978-94-010-0324-7_10
Publisher Name: Springer, Dordrecht
Print ISBN: 978-94-010-3872-0
Online ISBN: 978-94-010-0324-7
eBook Packages: Springer Book Archive