A modified particle swarm optimization procedure for triggering fuzzy flip-flop neural networks

• Autorzy: Kowalski Piotr A. , Słoczyński Tomasz

Identyfikatory

DOI

10.34768/amcs-2021-0039

• Języki publikacji: EN

Abstrakty

EN

The aim of the presented study is to investigate the application of an optimization algorithm based on swarm intelligence to the configuration of a fuzzy flip-flop neural network. Research on solving this problem consists of the following stages. The first one is to analyze the impact of the basic internal parameters of the neural network and the particle swarm optimization (PSO) algorithm. Subsequently, some modifications to the PSO algorithm are investigated. Approximations of trigonometric functions are then adopted as the main task to be performed by the neural network. As a result of the numerical verification of the problem, a set of rules are developed that can be helpful in constructing a fuzzy flip-flop type neural network. The obtained results of the computations significantly simplify the structure of the neural network in relation to similar conditions known from the literature.

Słowa kluczowe

EN

fuzzy neural network; fuzzy flip-flop neuron; particle swarm optimization; training procedure

PL

sieć neuronowa rozmyta; optymalizacja rojem cząstek; procedura szkoleniowa

• Wydawca: Oficyna Wydawnicza Uniwersytetu Zielonogórskiego
• Czasopismo: International Journal of Applied Mathematics and Computer Science
• Rocznik: 2021
• Tom: Vol. 31, no. 4
• Strony: 577--586
• Opis fizyczny: Bibliogr. 29 poz., rys., tab.

Twórcy

autor

Kowalski Piotr A.

• Faculty of Physics and Applied Computer Science, AGH University of Science and Technology, al. A. Mickiewicza 30, 30-059 Cracow, Poland; Systems Research Institute, Polish Academy of Sciences, ul. Newelska 6, 01-447 Warsaw, Poland

autor

Słoczyński Tomasz

• Faculty of Physics and Applied Computer Science, AGH University of Science and Technology, al. A. Mickiewicza 30, 30-059 Cracow, Poland

Bibliografia

• [1] Basha, S.S., Dubey, S.R., Pulabaigari, V. and Mukherjee, S. (2020). Impact of fully connected layers on performance of convolutional neural networks for image classification, Neurocomputing 378: 112–119.
• [2] Bodyanskiy, Y.V. and Tyshchenko, O.K. (2019). A hybrid cascade neuro-fuzzy network with pools of extended neo-fuzzy neurons and its deep learning, International Journal of Applied Mathematics and Computer Science 29(3): 477–488, DOI: 10.2478/amcs-2019-0035.
• [3] Carvalho, M. and Ludermir, T.B. (2006). Particle swarm optimization of feed-forward neural networks with weight decay, 6th International Conference on Hybrid Intelligent Systems (HIS’06), Rio de Janeiro, Brazil, pp. 5–5.
• [4] Chang, C.-H. (2015). Deep and shallow architecture of multilayer neural networks, IEEE Transactions on Neural Networks and Learning Systems 26(10): 2477–2486.
• [5] Chen, G. (2010). Simplified particle swarm optimization algorithm based on particles classification, 6th International Conference on Natural Computation, Yantai, China, Vol. 5, pp. 2701–2705.
• [6] Chen, M. (2008). Second generation particle swarm optimization, 2008 IEEE Congress on Evolutionary Computation (IEEE World Congress on Computational Intelligence), Hong Kong, China, pp. 90–96.
• [7] Eberhart, R.C. and Shi, Y. (2000). Comparing inertia weights and constriction factors in particle swarm optimization, Proceedings of the 2000 Congress on Evolutionary Computation, CEC00, La Jolla, USA, Vol. 1, pp. 84–88.
• [8] Gal, L., Botzheim, J. and Koczy, L.T. (2008). Improvements to the bacterial memetic algorithm used for fuzzy rule base extraction, IEEE International Conference on Computational Intelligence for Measurement Systems and Applications, Istanbul, Turkey, pp. 38–43.
• [9] Gál, L., Botzheim, J., Kóczy, L.T. and Ruano, A.E. (2009). Applying bacterial memetic algorithm for training feedforward and fuzzy flip-flop based neural networks, Joint 2009 International Fuzzy Systems Association World Congress and the European Society of Fuzzy Logic and Technology Conference, Lisbon, Portugal, pp. 1833–1838.
• [10] Gál, L., Lovassy, R. and Kóczy, L.T. (2010). Function approximation performance of fuzzy neural networks based on frequently used fuzzy operations and a pair of new trigonometric norms, International Conference on Fuzzy Systems, Barcelona, Spain, pp. 1–8.
• [11] Gniewek, L. and Kluska, J. (2004). Hardware implementation of fuzzy Petri net as a controller, IEEE Transactions on Systems, Man, and Cybernetics B: Cybernetics 34(3): 1315–1324.
• [12] Hirota, K. and Ozawa, K. (1989). The concept of fuzzy flip-flop, IEEE Transactions on Systems, Man, and Cybernetics 19(5): 980–997.
• [13] Hirota, K. and Pedrycz, W. (1993). Neurocomputations with fuzzy flip-flops, Proceedings of International Conference on Neural Networks (IJCNN-93), Nagoya, Japan, Vol. 2, pp. 1867–1870.
• [14] Kennedy, J. and Eberhart, R. (1995). Particle swarm optimization, Proceedings of the ICNN’95 International Conference on Neural Networks, Perth, Australia, Vol. 4, pp. 1942–1948.
• [15] Kowalski, P.A. (2013). Evolutionary strategy for the fuzzy flip-flop neural networks supervised learning procedure, International Conference on Artificial Intelligence and Soft Computing, Zakopane, Poland, pp. 294–305.
• [16] Lillicrap, T.P., Cownden, D., Tweed, D.B. and Akerman, C.J. (2016). Random synaptic feedback weights support error backpropagation for deep learning, Nature Communications 7(1): 1–10.
• [17] Lovassy, R., Kóczy, L.T. and Gál, L. (2008a). Applicability of fuzzy flip-flops in the implementation of neural networks, 9th International Symposium of Hungarian Researchers on Computational Intelligence and Informatics, CINTI 2008, Budapest, Hungary, pp. 333–344.
• [18] Lovassy, R., Koczy, L.T. and Gal, L. (2008b). Multilayer perceptron implemented by fuzzy flip-flops, IEEE International Conference on Fuzzy Systems (IEEE World Congress on Computational Intelligence), Hong, Kong, China, pp. 1683–1688.
• [19] Lovassy, R., Zavala, A.H., Gál, L., Nieto, O.C., Kóczy, L.T. and Batyrshin, I. (2010). Hardware implementation of fuzzy flip-flops based on Łukasiewicz norms, 9th WSEAS International Conference on Applied Computer and Applied Computational Science, Genova, Italy, pp. 196–201.
• [20] Łukasik, S. and Kowalski, P.A. (2014). Fully informed swarm optimization algorithms: Basic concepts, variants and experimental evaluation, Federated Conference on Computer Science and Information Systems, Warsaw, Poland, pp. 155–161.
• [21] Ozawa, K., Hirota, K. and Koczy, L.T. (1996). Fuzzy flip-flop, in M.Y. Patyra and D.M. Mlynek (Eds), Fuzzy Logic: Implementation and Applications,Wiley/ BG Teunbner Publ., pp. 197–236.
• [22] Ozawa, K., Hirota, K., Koczy, L.T. and Omori, K. (1991). Algebraic fuzzy flip-flop circuits, Fuzzy Sets and Systems 39(2): 215–226.
• [23] Pu, X., Fang, Z. and Liu, Y. (2007). Multilayer perceptron networks training using particle swarm optimization with minimum velocity constraints, in D. Liu et al. (Eds), Advances in Neural Networks, Lecture Notes in Computer Science, Vol. 493, Springer, Berlin/Heidelberg, pp. 237–245.
• [24] Rakitianskaia, A. and Engelbrecht, A. (2015). Saturation in PSO neural network training: Good or evil?, IEEE Congress on Evolutionary Computation (CEC), Sendai, Japan, pp. 125–132.
• [25] Rutkowski, L. (2008). Computational Intelligence: Methods and Techniques, Springer, Berlin/Heidelberg.
• [26] Siminski, K. (2021). An outlier-robust neuro-fuzzy system for classification and regression, International Journal of Applied Mathematics and Computer Science 31(2): 303–319, DOI: 10.34768/amcs-2021-0021.
• [27] Talbi, E.-G. (2009). Metaheuristics: From Design to Implementation, Wiley, Hoboken.
• [28] Tsoulos, I.G., Tzallas, A. and Karvounis, E. (2021). Improving the PSO method for global optimization problems, Evolving Systems 12: 1–9, DOI: 10.1007/s12530-020-09330-9.
• [29] Zavala, A.H., Nieto, O.C., Batyrshin, I. and Vargas, L.V. (2009). VLSI implementation of a module for realization of basic t-norms on fuzzy hardware, IEEE International Conference on Fuzzy Systems, Jeju, South Korea, pp. 655–659.

Uwagi

Opracowanie rekordu ze środków MNiSW, umowa Nr 461252 w ramach programu "Społeczna odpowiedzialność nauki" - moduł: Popularyzacja nauki i promocja sportu (2021).