Abstract
The aim of this paper is present the usage of (μ + λ) Evolutionary Strategy to evolve the architecture, and primarily the connection weights, for Fuzzy Flip-Flop Neural Networks. Due to the specific transfer function of this fuzzy-based neural network and its numerical derivatives, Back Propagation algorithm can be used for the training process, but it has very week convergence rates. Therefore Evolutionary Strategy as a heuristic learning algorithm will be applied here. In the article some numerical properties of proposed approach will be exposed. They will concern on natural example such as function approximation and data classification. It exhibits better results in terms of faster convergence and least square-error. Finally some conclusions and ideas for future work will be under discussion.
This is a preview of subscription content, log in via an institution.
Buying options
Tax calculation will be finalised at checkout
Purchases are for personal use only
Learn about institutional subscriptionsPreview
Unable to display preview. Download preview PDF.
References
Angulo, C., Parra, X., Catala, A.: K-SVCR. A Support Vector Machine for Multi-class Classification. Neurocomputing 55, 57–77 (2003)
Arabas, J.: Evolutionary Computation for Global Optimization – Current Trends. Journal of Telecommunications and Information Technology 4, 5–10 (2011)
Bergh, V.F., Engelbrecht, A.: Cooperative Learning in Neural Networks Using Particle Swarm Optimizers. South African Computer Journal 26, 84–90 (2000)
Brownlee, J.: Clever Algorithms: Nature-Inspired Programming Recipes, Lulu Enterprises (2011)
Gal, L., Botzheim, J., Koczy, L.T.: Improvements to the Bacterial Memetic Algorithm used for Fuzzy Rule Base Extraction. In: IEEE International Conference on Computational Intelligence for Measurement Systems and Applications, Istanbul, pp. 38–43 (2008)
Gal, L., Botzheim, J., Koczy, L.T.: Function Approximation Performance of Fuzzy Neural Networks Based on Frequently Used Fuzzy Operations and a Pair of New Trigonometric Norms. In: IEEE International Conference on Fuzzy Systems, Barcelona, pp. 1–8 (2010)
Diamond, J., Pedrycz, W., McLeod, D.: Fuzzy JK Flip-Flops as Computational Structures: Design and Implementation. IEEE Transactions on Circuits and Systems II, Analog and Digital Signal Processing 41(3), 215–226 (1994)
Gniewek, L., Kluska, J.: Family of Fuzzy JK Flip-Flops Based on Bounded Product, Bounded Sum and Complementation. IEEE Transactions on Systems, Man, and Cybernetics, Part B: Cybernetics 28(6), 861–868 (1998)
Hirota, K., Ozawa, K.: The Concept of Fuzzy Flip-Flop. Man and Cybernetics 19(5), 980–997 (1989)
Hirota, K., Pedrycz, W.: Neurocomputations with Fuzzy Flip-Flops. In: Proceedings of International Joint Conference on Neural Networks, Nagoya, vol. 2, pp. 1867–1870 (1993)
Jones, A.J.: Genetic Algorithms and Their Applications to the Design of Neural Networks. Neural Computing and Applications, 32–45 (1993)
De Jong, K.A.: Evolutionary Computation: A Unified Approach. MIT Press, Cambridge (2006)
Kacprzyk, J.: Fuzzy Sets in Systems Analysis. PWN, Warsaw (1986)
Kowalski, P.A., Kulczycki, P.: Data Sample Reduction for Classification of Interval Information using Neural Network Sensitivity Analysis. In: Dicheva, D., Dochev, D. (eds.) AIMSA 2010. LNCS, vol. 6304, pp. 271–272. Springer, Heidelberg (2010)
Kowalski, P.A., Lukasik, S., Charytanowicz, M., Kulczycki, P.: Data-Driven Fuzzy Modelling and Control with Kernel Density Based Clustering Technique. Polish Journal of Environmental Studies 17, 83–87 (2008)
Koczy, L.T., Lovassy, R.: Fuzzy Flip-Flops and Neural Nets? In: IEEE International Fuzzy Systems Conference, London, pp. 1–6 (2007)
Kulczycki, P.: Statistical Inference for Fault Detection: A Complete Algorithm Based on Kernel Estimators. Kybernetika 38(2), 141–168 (2002)
Kulczycki, P., Kowalski, P.A.: Bayes Classification of Imprecise Information of Interval Type. Control and Cybernetics 40(1), 101–123 (2011)
Kulczycki, P., Hryniewicz, O., Kacprzyk, J. (eds.): Information Technologies for Systems Research. WNT, Warsaw (2007) (in Polish)
Kulczycki, P., Charytanowicz, M., Kowalski, P.A., Lukasik, S.: The Complete Gradient Clustering Algorithm: Properties in Practical Applications. Journal of Applied Statistics 39(6), 1211–1224 (2012)
Lovassy, R., Koczy, L.T., Gal, L.: Multilayer Perception Implemented by Fuzzy Flip-Flops. In: IEEE World Congress on Computational Intelligence, Hong Kong, pp. 1683–1688 (2008)
Lovassy, R., Koczy, L.T., Gal, L.: Optimizing Fuzzy Flip-Flop Based Neural Networks by Bacterial Memetic Algorithm. In: IFSA/EUSFLAT, Lisbon, pp. 1508–1513 (2009)
Lukasik, S., Kowalski, P.A., Charytanowicz, M., Kulczycki, P.: Fuzzy Model Identification Using Kernel-Density-Based Clustering. In: Atanassov, K., Chountas, P., Kacprzyk, J., Krawczak, M.P., Melo-Pinto, P., Szmidt, E., Zadrozny, S. (eds.) Developments in Fuzzy Sets, Intuitionistic Fuzzy Nets and Related Topics. Applications, vol. II, pp. 135–146. EXIT, Warszawa (2008)
Ozawa, K., Hirota, K., Koczy, L.T.: Fuzzy flip-flop. In: Patyra, M.J., Mlynek, D.M. (eds.) Fuzzy Logic Implementation and Applications, pp. 97–236. Wiley (1996)
Mandziuk, J.: Solving the N-Queens Problem with a Binary Hopfield-Type Network. Biological Cybernetics 72(5), 439–446 (1995)
Marquardt, D.: An Algorithm for Least-Squares Estimation of Nonlinear Parameters. Journal of Applied Mathematics 11, 431–441 (1963)
Rutkowski, L.: Computational Intelligence: Methods and Techniques. Springer, Berlin (2008)
Whitley, D., Starkweather, T., Bogart, C.: Genetic Algorithms and Neural Networks: Optimizing Connections and Connectivity. Technical Report Department of Computer Science, Colorado State University, pp. 89–117 (1989)
Iris Data Set, http://archive.ics.uci.edu/ml/datasets/Iris
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2013 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Kowalski, P.A. (2013). Evolutionary Strategy for the Fuzzy Flip-Flop Neural Networks Supervised Learning Procedure. In: Rutkowski, L., Korytkowski, M., Scherer, R., Tadeusiewicz, R., Zadeh, L.A., Zurada, J.M. (eds) Artificial Intelligence and Soft Computing. ICAISC 2013. Lecture Notes in Computer Science(), vol 7894. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-38658-9_27
Download citation
DOI: https://doi.org/10.1007/978-3-642-38658-9_27
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-38657-2
Online ISBN: 978-3-642-38658-9
eBook Packages: Computer ScienceComputer Science (R0)