Abstract
The paper presents new approach the idea of artificial neural network (ANN) modelling and design with the use of calculus of finite differences proposed by Dudek-Dyduch [5, 8] and then developed jointly with Tadeusiewicz [5] and others. Previously such neural nets were applied mainly to the extraction of different features i.e. edges, ridges, maxima, extrema and many others that can be defined with the use of a classic derivative of any order and their linear combinations. The author extend this method of ANN modelling by the use of fractional derivative theory for transfer function modelling. Different types of fractional derivatives and their numerical accuracy have been presented. Finally it was shown that the discrete approximation of fractional derivative of some base functions allows for modelling the transfer function of a single neuron for various characteristics. In such an approach, the smooth control of a derivative order allows the neuron dynamics to be modeled without direct modification of the source code in the IT model. The novel approach universalizes the model of the artificial neurons.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Cao, L.D., Rodriguez-Lopez, R.: From fractional order equations to integer order equations. Fract. Calc. Appl. Anal. 20(6), 1405–1423 (2017)
Ding, H., Li, C.: High-order algorithms for Riesz derivative and their applications. Numer. Methods Partial Differ. Equ. 33(5), 1754–1794 (2017)
Drałus, G.: Global models of dynamic complex systems – modelling using the multilayer neural networks. Ann. UMCS Sectio AI Inform. 7(1), 61–71 (2007)
Dudek-Dyduch, E.: Algebraic logical meta-model of decision processes - new metaheuristics. In: Artificial Intelligence and Soft Computing, ICAISC, pp. 541–554 (2015)
Dudek-Dyduch, E., Tadeusiewicz, R.: Neural networks indicating maxima and ridges in two-dimensional signal. In: EAANN, FAIS - Helsinki, pp. 485–488 (1995)
Garrappa, R.: Numerical evaluation of two and three parameter Mittag-Leffler functions. SIAM J. Numer. Anal. 53(3), 1350–1369 (2015)
Ghosh, U., Sarkar, S., Das, S.: Solution of system of linear fractional differential equations with modified derivative of Jumarie type. Am. J. Math. Anal. 3(3), 72–84 (2015)
Gomolka, Z.: Neural networks in the analysis of fringe images. Ph.D. thesis (2000). (in Polish)
Gomolka, Z., Dudek-Dyduch, E., Kondratenko, Y.P.: From homogeneous network to neural nets with fractional derivative mechanism. In: ICAISC 2017. Lecture Notes in Computer Science, vol. 10245 (2017)
Ding, H., Li, C., Chen, Y.: High-order algorithms for Riesz derivative and their applications. J. Comput. Phys. 293, 218–237 (2015)
Kondratenko, Y.P., Sidenko, I.V.: Design and reconfiguration of intelligent knowledge-based system for fuzzy multi-criterion decision making in transport logistics. J. Comput. Optim. Econ. Financ. 6, 229–242 (2014)
Kwater, T., Bartman, J.: Application of artificial neural networks in non-invasive identification of electric energy receivers. In: PAEE, Koscielisko, pp. 1–6 (2017)
Luo, W.-H., Li, C., Huang, T.-Z., Gu, X.-M., Wu, G.-C.: A high-order accurate numerical scheme for the caputo derivative with applications to fractional diffusion problems. Numer. Funct. Anal. Optim. 39(5), 600–622 (2018)
Mazurkiewicz, J.: Dependability metrics for network systems—analytical and experimental analysis. In: Dependability Engineering and Complex Systems. Advances in Intelligent Systems and Computing, vol. 470 (2016)
Ortigueira, M.D., Machado, J.T.: What is a fractional derivative? J. Comput. Phys. 293, 4–13 (2015)
McClelland, J.L.: Explorations in Parallel Distributed Processing: A Handbook of Models, Programs, and Exercises. MIT Press, Cambridge (2015)
Minsky, M., Papert, S.: Perceptrons: An Introduction to Computational Geometry, Expanded Edition Paperback. The MIT Press, Cambridge (1987). ISBN 0-262-63022-2
Moret, I.: Shift-and-invert Krylov methods for time-fractional wave equations. Numer. Funct. Anal. Optim. 36(1), 86–103 (2015)
Olchawa, A., Walkowiak, T.: Automatic reconfiguration in the response to network incidents by neural networks. In: Al-Dahoud, A. (ed.) ICIT 2009, Amman, Jordan, 3–5 June 2009, pp. 83–89. Al-Zaytoonah University of Jordan, Amman (2009)
Ortigueira, M.D.: Riesz potential operators and inverses via fractional centered derivatives. Int. J. Math. Math. Sci. 2006, 1–12 (2006). Article ID 48391
Oustaloup, A., Levron, F., Mathieu, B., Nanot, F.M.: Frequency-band complex noninteger differentiator: characterization and synthesis. IEEE Trans. Circ. Syst. I: Fundam. Theory Appl. I. 47, 25–39 (2000)
Petraš, I.: Fractional Derivatives, Fractional Integrals, and Fractional Differential Equations in Matlab. In: Computer and Information Science – Engineering Education and Research Using MATLAB, pp. 239–264 (2011). ISBN 978-953-307-656-0
Podlubny, I.: Matrix approach to discrete fractional calculus. Fract. Calc. Appl. Anal. 3, 359–386 (2000)
Sheng, H., Li, Y., Chen, Y.Q.: Application of numerical inverse Laplace transform algorithms in fractional calculus. J. Franklin Inst. 348, 315–330 (2011)
Schmidhuber, J.: Who Invented Backpropagation? (2014) (updated 2015). http://people.idsia.ch/~juergen/who-invented-backpropagation.html
Twaróg, B., Gomółka, Z., Żesławska, E.: Time analysis of data exchange in distributed control systems based on wireless network model. In: Lecture Notes in Electrical Engineering, vol. 452, pp. 333–342 (2018)
Twarog, B., Pekala, R., Bartman, J., Gomolka, Z.: The changes of air gap in inductive engines as vibration indicator aided by mathematical model and artificial neural network, DCDS - Series A Issue Supplement, September 2007
Vinagre, B.M., Podlubny, I., Hernández, A., Feliu, V.: Some approximations of fractional order operators used in control theory and applications. Fract. Calc. Appl. Anal. 3, 231–248 (2000)
Xue, D.: Computational aspect of fractional-order control problems. In: Tutorial Workshop on Fractional Order Dynamic Systems and Controls, Proceedings of the WCICA 2010 (2010)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2019 Springer International Publishing AG, part of Springer Nature
About this paper
Cite this paper
Gomolka, Z. (2019). Neurons’ Transfer Function Modeling with the Use of Fractional Derivative. In: Zamojski, W., Mazurkiewicz, J., Sugier, J., Walkowiak, T., Kacprzyk, J. (eds) Contemporary Complex Systems and Their Dependability. DepCoS-RELCOMEX 2018. Advances in Intelligent Systems and Computing, vol 761. Springer, Cham. https://doi.org/10.1007/978-3-319-91446-6_21
Download citation
DOI: https://doi.org/10.1007/978-3-319-91446-6_21
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-91445-9
Online ISBN: 978-3-319-91446-6
eBook Packages: Intelligent Technologies and RoboticsIntelligent Technologies and Robotics (R0)