Abstract
Generally, math models which use the “continuous mathematics” are dominant in the construction of modern digital devices, while the discrete basis remain without much attention. However, when solving the problem of constructing effective computing devices it is impossible to ignore the compatibility level of the mathematical apparatus and the computer platform used for its implementation. In the field of artificial intelligence, this problem becomes urgent during the development of specialized computers based on the neural network paradigm. In this paper, the disadvantages of the application of existing approaches to the construction of a neural network basis are analyzed. A new method for constructing a neural-like architecture based on discrete trainable structures is proposed to improve the compatibility of artificial neural network models in the digital basis of programmable logic chips and general-purpose processors. A model of a gate neural network using a mathematical apparatus of Boolean algebra is developed. Unlike formal models of neural networks, proposed network operates with the concepts of discrete mathematics. Formal representations of the gate network are derived. The learning algorithm is offered.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Aljautdinov, M.A., Galushkin, A.I., Kazancev, P.A., Ostapenko, G.P.: Neurocomputers: from software to hardware implementation, p. 152. Gorjachaja linija - Telekom, Moscow (2008). (in Russian)
Mezenceva, O.S., Mezencev, D.V., Lagunov, N.A., Savchenko, N.S.: Implementations of non-standard models of neuron using Neuromatrix. Izvestija JuFU. Tehnicheskie nauki 131(6), 178–182 (2012). (in Russian)
Adetiba, E., Ibikunle, F.A., Daramola, S.A., Olajide, A.T.: Implementation of efficient multilayer perceptron ANN neurons on field programmable gate array chip. Int. J. Eng. Technol. 14(1), 151–159 (2014)
Manchev, O., Donchev, B., Pavlitov, K.: FPGA implementation of artificial neurons. Electronics: An Open Access Journal, Sozopol, Bulgaria, 22–24 September (2004). https://www.researchgate.net/publication/251757109_FPGA_IMPLEMENTATION_OF_ARTIFICIAL_NEURONS. Accessed 28 Jan 2017
Kohut R., Steinbach B.: The Structure of Boolean Neuron for the Optimal Mapping to FPGAs. http://www.informatik.tu-freiberg.de/prof2/publikationen/CADSM2005_BN_FPGA.pdf. Accessed 1 Feb 2017
Korani, R., Hajera, H., Imthiazunnisa, B., Chandra Sekhar, R.: FPGA modelling of neuron for future artificial intelligence applications. Int. J. Adv. Res. Comput. Commun. Eng. 2(12), 4763–4768 (2013)
Omondi, A. R., Rajapakse, J. C.: FPGA Implementations of Neural Networks. Springer (2006). http://lab.fs.uni-lj.si/lasin/wp/IMIT_files/neural/doc/Omondi2006.pdf. Accessed 28 Jan 2017
Gribachev, V.: Element base of hardware implementations of neural networks (in Russian). http://kit-e.ru/articles/elcomp/2006_8_100.php. Accessed 30 June 2016
Mikhailyuk, T. E., Zhernakov, S. V.: Increasing efficiency of using FPGA resources for implementation neural networks. In: Nejrokomp’jutery: razrabotka, primenenie, vol. 11, pp. 30–39 (2016). (in Russian)
Mikhailyuk, T.E., Zhernakov, S.V.: On an approach to the selection of the optimal FPGA architecture in neural network logical basis. Informacionnye tehnologii 23(3), 233–240 (2017). (in Russian)
Kohut, R., Steinbach, B.: Decomposition of Boolean Function Sets for Boolean Neural Networks. https://www.researchgate.net/publication/228865096_Decomposition_of_Boolean_Function_Sets_for_Boolean_Neural_Networks. Accessed 1 Feb 2017
Anthony, M.: Boolean Functions and Artificial Neural Networks. http://www.cdam.lse.ac.uk/Reports/Files/cdam-2003–01.pdf. Accessed 29 Jan 2017
Kohut, R., Steinbach, B.: Boolean neural networks. WSEAS Trans. Syst. 3(2), 420–425 (2004)
Steinbach, B., Kohut, R.: Neural Networks – A Model of Boolean Functions. https://www.researchgate.net/publication/246931125_Neural_Networks_-_A_Model_of_Boolean_Functions. Accessed 1 Feb 2017
Vinay, D.: Mapping boolean functions with neural networks having binary weights and zero thresholds. IEEE Trans. Neural Netw. 12(3), 639–642 (2001)
Zhang, C., Yang, J., Wu, W.: Binary higher order neural networks for realizing boolean functions. IEEE Trans. Neural Netw. 22(5), 701–713 (2011)
Rademacher, H.: Einige Sätze über Reihen von allgemeinen Orthogonalfunktionen. Math. Ann. 87(1–2), 112–138 (1922)
Hajkin, S.: Neural networks: a comprehensive foundation. Vil’jams, Moscow (2008). (in Russian)
Osovskij, S.: Neural networks for information processing, p. 344. Finansy i statistika, Moskow (2002). (in Russian)
Shin, Y., Ghosh, J.: Efficient higher-order neural networks for classification and function approximation. The University of Texas at Austin (1995). https://www.researchgate.net/publication/2793545_Efficient_Higher-order_Neural_Networks_for_Classification_and_Function_Approximation. Accessed 28 Jan 2017
Shevelev Ju, P.: Discrete mathematics. Part 1: The theory of sets. Boolean algebra (Automated learning technology “Symbol”), p. 118. TUSUR University, Tomsk (2003). (in Russian)
Omondi, A., Premkumar, B.: Residue number systems: theory and implementation, p. 312. Imperial College Press, London (2007)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2018 Springer International Publishing AG
About this paper
Cite this paper
Mikhailyuk, T., Zhernakov, S. (2018). Implementation of a Gate Neural Network Based on Combinatorial Logic Elements. In: Kryzhanovsky, B., Dunin-Barkowski, W., Redko, V. (eds) Advances in Neural Computation, Machine Learning, and Cognitive Research. NEUROINFORMATICS 2017. Studies in Computational Intelligence, vol 736. Springer, Cham. https://doi.org/10.1007/978-3-319-66604-4_4
Download citation
DOI: https://doi.org/10.1007/978-3-319-66604-4_4
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-66603-7
Online ISBN: 978-3-319-66604-4
eBook Packages: EngineeringEngineering (R0)