Abstract
The paper refers to ANNs of the feed-forward type, homogeneous within individual layers. It extends the idea of network modelling and design with the use of calculus of finite differences proposed by Dudek-Dyduch E. and then developed jointly with Tadeusiewicz R. and others. This kind of neural nets was applied mainly to different features extraction i.e. edges, ridges, maxima, extrema and many others that can be defined with the use of classic derivative of any order and their linear combinations. Authors extend this type ANNs modelling by using fractional derivative theory. The formulae for weight distribution functions expressed by means of fractional derivative and its discrete approximation are given. It is also shown that the application of 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 smooth control of a derivative order allows to model the neuron dynamics without direct modification of the source code in IT model. The new approach presented in the paper, universalizes the model of the considered type of ANNs.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Chi, C., Gao, F.: Simulating fractional derivatives using matlab. J. Softw. 8(3), 572–578 (2013)
Chang, O., Constante, P., Gordon, A.: A novel deep neural network that uses space-time features for tracking and recognizing a moving object (2017). https://doi.org/10.1515/jaiscr-2017-0009. Accessed 23 Feb 2017
Vance, D.: Fractional derivatives and fractional mechanics, 2 June 2014
Dudek-Dyduch, E., Tadeusiewicz, R.: Neural networks indicating maxima and ridges in two-dimensional signal. In: Engineering Applications of Artificial Neural Networks, pp. 485–488. FAIS- Helsinki (1995)
Dudek-Dyduch, E.: Artificial neuron network indicating distribution of local maxima of input signals Ph.D. thesis, AGH-University of Science and Technology (1977)
Dudek-Dyduch, E., Dyduch, T.: Application of neural networks in 3D object recognition system. Int. J. Pattern Recog. Artif. Intell. 12(4), 491–504 (1998)
Dudek-Dyduch, E.: Synthesis of feed forward neural network indicating extremes. Int. J. Syst. Anal. Model. Simul. 24(1996), 135–151 (1996)
Dudek-dyduch, E., Tadeusiewicz, R., Horzyk, A.: Neural network adaptation process effectiveness dependent of constant training data availability. Neurocomputing 72(13), 3138–3149 (2009). ISSN:0925–2312
Gomolka, Z., Twarog, B., Bartman, J.: Improvement of image processing by using Homogeneous neural networks with fractional derivatives theorem. Discret. Contin. Dyn. Syst. 31(Supplement), 505–514 (2011)
Gomolka, Z., Twarog, B.: Artificial intelligence methods for image processing. In: Symbiosis of Engineering and Computer Science, pp. 93–124 (2010)
Gomolka, Z., Twarog, B., Kwiatkowski, B.: The fractional order operators applied in the image processing. In: Computing in Science and Technology, Monographs in AI, pp. 77–96 (2013)
Gomolka, Z.: Neural network for fringe image analysis, Academy of Mining and Metallurgy Cracow, Ph.D. thesis (2000)
Kondratenko, Y., Gordienko, E.: Implementation of the neural networks for adaptive control system on FPGA. In: DAAAM International, Vienna, Austria, EU, pp. 0389–0392 (2012)
Kondratenko, Y.P., Kozlov, O.V., Gerasin, O.S., Zaporozhets, Y.M.: Synthesis and research of neuro-fuzzy observer of clamping force for mobile robot automatic control system. In: IEEE First International Conference on Data Stream Mining & Processing (DSMP), pp. 90–95 (2016). doi:10.1109/DSMP.2016.7583514
Korytkowski, M., Rutkowski, L., Scherer, R.: Fast image classification by boosting fuzzy classifiers. Inf. Sci. 327, 175–182 (2016)
Neel, M.C., Joelson, M.: Generalizing Grunwald-Letnikovs formulas for fractional derivatives, ENOC-2008, Saint Petersburg, Russia, June 30–July 4 (2008)
Chakraborty, M., Maiti, D., Konar, A., Janarthanan, R.: A study of the Grunwald-Letnikov definition for minimizing the effects of random noise on fractional order differential equations. In: 4th IEEE International Conference on Information and Automation for Sustainability (2008)
Ostalczyk, P.: On simplified forms of the fractional-order backward difference and related fractional-order linear discrete-time system description. Bull. Polish Acad. Sci. Techn. Sci. 63(2), 423–433 (2015)
Ostalczyk, P.: Discrete Fractional Calculus Applications in Control and Image Processing. World Scientific Publishing Co., Pte. Ltd., Singapore (2016)
Tadeusiewicz, R.: Neural networks as a tool for modelling of biological systems. Bio Algorithms Med. Syst. 11(3), 135–144 (2015). doi:10.1515/bams-2015-0021
Tadeusiewicz, R., Chaki, R., Chaki, N.: Exploring Neural Networks with C#. CRC Press, Taylor & Francis Group, Boca Raton (2014)
Garg, V., Singh, K.: An improved Grunwald-Letnikov fractional differential mask for image texture enhancement. IJACSA 3(3), 130–135 (2012)
Acknowledgments
The research were conducted in the scientific cooperation between Faculty of Mathematics and Natural Sciences Department of Computer Engineering at University of Rzeszow and AGH University of Science and Technology Cracow, Department of Biomedical Engineering and Automation. The studies were conducted in the laboratory of Computer Graphics and Digital Image Processing at Center for Innovation and Transfer of Natural Sciences and Engineering Knowledge of Rzeszow University. Grants: WMP/GD-11/2016 and AGH-UST 11.120.417.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2017 Springer International Publishing AG
About this paper
Cite this paper
Gomolka, Z., Dudek-Dyduch, E., Kondratenko, Y.P. (2017). From Homogeneous Network to Neural Nets with Fractional Derivative Mechanism. In: Rutkowski, L., Korytkowski, M., Scherer, R., Tadeusiewicz, R., Zadeh, L., Zurada, J. (eds) Artificial Intelligence and Soft Computing. ICAISC 2017. Lecture Notes in Computer Science(), vol 10245. Springer, Cham. https://doi.org/10.1007/978-3-319-59063-9_5
Download citation
DOI: https://doi.org/10.1007/978-3-319-59063-9_5
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-59062-2
Online ISBN: 978-3-319-59063-9
eBook Packages: Computer ScienceComputer Science (R0)