Abstract
The disadvantages of the fuzzy BP learning are its low speed of error convergence and the high possibility of trapping into local minima. In this paper, a fuzzy proportional factor is added to the fuzzy BP’s iteration scheme to enhance the convergence speed. The added factor makes the proposed method more dependant on the distance of actual outputs and desired ones. Thus in contrast with the conventional fuzzy BP, when the slop of error function is very close to zero, the algorithm does not necessarily return almost the same weights for the next iteration. According to the simulation’s results, the proposed method is superior to the fuzzy BP in terms of generated error.
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
Aliev, R.A., Fazlollahi, B., Vahidov, R.M.: Genetic algorithm-based learning of fuzzy neural network, Part 1: feed-forward fuzzy neural networks. Fuzzy Sets and Systems 118(2), 351–358 (2001)
Buckley, J.J., Hayashi, Y.: Direct fuzzification of neural networks. In: 1st Asian Fuzzy System Symposium, pp. 560–567 (1993)
Cai, H., Sun, D., Cao, Q., Pu, F.: A novel BP algorithm based on three-term and applica-tion in service selection of ubiquitous. In: 9th International Conference on Computing, Control, Automation, Robotics and Vision, pp. 1–6 (2006)
Ishibuchi, H., Kwon, K., Tanaka, H.A.: Learning of fuzzy neural networks with triangular fuzzy weights. Fuzzy Sets and Systems 71(3), 277–293 (1995)
Lee, S.C., Lee, E.T.: Fuzzy sets and neural networks. Journal of Cybernetics 4, 83–103 (1974)
Liu, P., Hongxing, L.: Efficient learning algorithms for three-layer feedforward regular fuzzy neural networks. IEEE Trans. On Neural Networks 15(2), 545–558 (2004)
Mashichi, M.H., Mashinchi, M.R., Shamsuddin, S.M., Pedrycz, W.: Genetically tuned fuzzy BP learning method based on derivation of min-max function for fuzzy neural networks. In: International Conference on Genetic and Evolutionary Methods Nevada, pp. 213–219 (2007)
Narazaki, H., Ralescu, L.A.: A method to implement qualitative knowledge in multi-layered neural networks. Fuzzy Logic and Fuzzy Control, 82–95 (1991)
Shamsuddin, S.M., Saman, F.I., Darus, M.: Three backpropagatiopn algorithm for classification problem. Neural Network World 17(4), 363–376 (2007)
Zweiri, Y.H., Seneviratne, L.D.: Optimization and stability of a three-term BP algorithm Neural networks. In: CI 2000, pp. 1514–1540 (2000)
Zweiri, H.Y., Whidborne, J.F., Althoefer, K., Seneviratne, L.D.: A three-term backpropagation algorithm. Neurocomputing 50, 305–318 (2003)
Zweiri, H.Y., Seneviratne, L.D., Althoefer, K.: Stability analysis of a three-term back-propagation algorithm. Neural Networks 18, 1341–1347 (2005)
Liu, P.: Representation of digital image by fuzzy neural network. Fuzzy Sets and Systems 130(1), 109–123 (2002)
Abbasbandy, S., Otadi, M.: Numerical solution of fuzzy polynomials by fuzzy neural networks. Applied Mathematics and Computations 181(2), 1084–1089 (2006)
Abbasbandy, S., Neirto, J.J., Amirfagharian, M.: Best approximation of fuzzy functions. Nonlinear Studies 14(1), 87–102 (2007)
Kuo, R.J., Wu, P., Wang, C.P.: An intelligent sales forcasting system through integration of artificial intelligence and fuzzy neural networks with fuzzy weight elimination. Neural networks 15(7), 909–925 (2002)
Fukuda, S., Hiramatsu, K., Mori, M.: Fuzzy neural network model for habitat prediction and HEP for habitat quality estimation focusing on Japanese medaka (Oryais latipes) in agricultural canals. Paddy Water Environ. 4(3), 119–124 (2006)
Ishibuchi, H., Tanaka, H.: Regression analysis with internal model by neural net. In: Proc. Internat. Joint Conf. on Neural Networks, pp. 1594–1599 (1991)
Miyazaki, A., Kwan, K., Ishibuchi, H., Tanaka, H.: Fuzzy regression analysis by fuzzy neural networks and its application. IEEE Transactions on Fuzzy Systems (1995)
Klir, G.J., Yuan, B.: Fuzzy sets and fuzzy logic: theory and applications. Prentice Hall PTR, New York (1995)
Kosko, B.: Fuzzy associated memories. In: Kandel, A. (ed.) Fuzzy expert systems, Addison-Weley, Reading (1987)
Liu, P., Li, H.X.: Fuzzy neural network theory and application. World Scientific, River Edge (2004)
Saman, F.I.: Three-term backpropagation algorithm for classification problem. Master Thesis Universiti Teknologi Malaysia, Malaysia (2006)
Buckley, J., Hayashi, Y.: Fuzzy neural networks. In: Yager, R., Zadeh, L. (eds.) Fuzzy Sets, Neural Networks, and Soft Computing. Van Nostrand Reinhold, New York (1994)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2009 Springer-Verlag Berlin Heidelberg
About this chapter
Cite this chapter
Mashinchi, M.H., Shamsuddin, S.M.H.J. (2009). Three-Term Fuzzy Back-Propagation. In: Hassanien, AE., Abraham, A., Vasilakos, A.V., Pedrycz, W. (eds) Foundations of Computational, Intelligence Volume 1. Studies in Computational Intelligence, vol 201. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-01082-8_6
Download citation
DOI: https://doi.org/10.1007/978-3-642-01082-8_6
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-01081-1
Online ISBN: 978-3-642-01082-8
eBook Packages: EngineeringEngineering (R0)