Abstract
Any real continuous bounded function of many variables is representable as a superposition of functions of one variable and addition. Depending on the type of superposition, the requirements for the functions of one variable differ. The article investigated one of the options for the numerical implementation of such a superposition proposed by Sprecher. The superposition was presented as a three-layer Feedforward neural network, while the functions of the first’s layer were considered as a generator of space-filling curves (Peano curves). The resulting neural network was applied to the problems of direct kinematics of parallel manipulators.
References
[1] Khalapyan S.Y., Glushchenko A.I., Rybak L.A., Gaponenko E.V., Malyshev D.I., Intelligent Computing Based on Neural Network Model in Problems of Kinematics and Control of Parallel Robot, in 2018 3rd Russian-Pacific Conference on Computer Technology and Applications (RPC), IEEE, 2018, 1–5Suche in Google Scholar
[2] Kolmogorov A., On the representation of continuous functions of several variables by superposition of continuous functions of one variable and addition, in Dokl. Akad. Nauk, volume 114, 1957, 953–956Suche in Google Scholar
[3] Arnol’d V.I., O funktsiyakh trekh peremennykh, in Doklady Akademii nauk, volume 114, Rossiyskaya akademiya nauk, 1957, 679–681Suche in Google Scholar
[4] Arnol’d V.I., O predstavimosti funktsiy dvukh peremennykh v vide X[ϕ(x)+ψ(y)], Uspekhi matematicheskikh nauk, 12(2 (74), 1957, 119–121Suche in Google Scholar
[5] Sprecher D.A., A representation theorem for continuous functions of several variables, Proceedings of the American Mathematical Society, 16(2), 1965, 200–20310.1090/S0002-9939-1965-0174666-7Suche in Google Scholar
[6] Sprecher D.A., On the structure of continuous functions of several variables, Transactions of the American Mathematical Society, 115, 1965, 340–35510.1090/S0002-9947-1965-0210852-XSuche in Google Scholar
[7] Sprecher D.A., An improvement in the superposition theorem of Kolmogorov, Journal of Mathematical Analysis and Applications, 38(1), 1972, 208–21310.1016/0022-247X(72)90129-1Suche in Google Scholar
[8] Sprecher D.A., A universal mapping for Kolmogorov’s superposition theorem, Neural Networks, 6(8), 1993, 1089–109410.1016/S0893-6080(09)80020-8Suche in Google Scholar
[9] Sprecher D.A., A numerical implementation of Kolmogorov’s superpositions II, Neural Networks, 10(3), 1997, 447–45710.1016/S0893-6080(96)00073-1Suche in Google Scholar
[10] Hecht-Nielsen R., Kolmogorov’s mapping neural network existence theorem, in Proceedings of the international conference on Neural Networks, volume 3, IEEE Press New York, 1987, 11–14Suche in Google Scholar
[11] Hecht-Nielsen R., Counterpropagation networks, Applied optics, 26(23), 1987, 4979–498410.1364/AO.26.004979Suche in Google Scholar
[12] Kurková V., Kolmogorov’s theorem and multilayer neural networks, Neural networks, 5(3), 1992, 501–50610.1016/0893-6080(92)90012-8Suche in Google Scholar
[13] Cybenko G., Approximation by superpositions of a sigmoidal function, Mathematics of control, signals and systems, 2(4), 1989, 303–31410.1007/BF02551274Suche in Google Scholar
[14] Cybenko G., Approximation by superpositions of a sigmoidal function, Mathematics of Control, Signals, and Systems (MCSS), 5(4), 1992, 455–45510.1007/BF02134016Suche in Google Scholar
[15] Girosi F., Poggio T., Representation properties of networks: Kolmogorov’s theorem is irrelevant, Neural Computation, 1(4), 1989, 465–46910.1162/neco.1989.1.4.465Suche in Google Scholar
[16] Sergeyev Y.D., Strongin R.G., Lera D., Introduction to global optimization exploiting space-filling curves, Springer Science & Business Media, 201310.1007/978-1-4614-8042-6Suche in Google Scholar
[17] Skilling J., Programming the Hilbert curve, in AIP Conference Proceedings, volume 707, AIP, 2004, 381–38710.1063/1.1751381Suche in Google Scholar
[18] Lera D., Posypkin M., Sergeyev Y.D., Approximating the solution set of nonlinear inequalities by using Peano space-filling curves, Numerical Computations: Theory and Algorithms NUMTA 2019, 2019, 204Suche in Google Scholar
[19] Lera D., Sergeyev Y.D., Deterministic global optimization using space-filling curves and multiple estimates of Lipschitz and Hölder constants, Communications in Nonlinear Science and Numerical Simulation, 23(1-3), 2015, 328–34210.1016/j.cnsns.2014.11.015Suche in Google Scholar
[20] Yang G., Yang X., Wang P., Arithmetic-Analytic Representation of Peano Curve, International Journal of Mathematics and Mathematical Sciences, 2019, 201910.1155/2019/6745202Suche in Google Scholar
[21] Evtushenko Y., Posypkin M., Turkin A., Rybak L., The non-uniform covering approach to manipulator workspace assessment, in 2017 IEEE Conference of Russian Young Researchers in Electrical and Electronic Engineering (EIConRus), IEEE, 2017, 386–38910.1109/EIConRus.2017.7910573Suche in Google Scholar
[22] Gorchakov A., Ignatov A., Malyshev D., Posypkin M., Parallel algorithm for approximating the work space of a robot, International Journal of Open Information Technologies, 7(1), 2019, 1–7Suche in Google Scholar
[23] Köppen M., On the training of a Kolmogorov Network, in International Conference on Artificial Neural Networks, Springer, 2002, 474–47910.1007/3-540-46084-5_77Suche in Google Scholar
[24] Zein M., Wenger P., Chablat D., Non-singular assembly-mode changing motions for 3-RPR parallel manipulators, Mechanism and Machine Theory, 43(4), 2008, 480–49010.1016/j.mechmachtheory.2007.03.011Suche in Google Scholar
[25] Wenger P., Chablat D., Kinematic analysis of a class of analytic planar 3-RPR parallel manipulators, in Computational Kinematics, Springer, 2009, 43–5010.1007/978-3-642-01947-0_6Suche in Google Scholar
[26] Evtushenko Y., Posypkin M., Rybak L., Turkin A., Approximating a solution set of nonlinear inequalities, Journal of Global Optimization, 71(1), 2018, 129–14510.1007/s10898-017-0576-zSuche in Google Scholar
[27] Wenger P., Chablat D., Zein M., Degeneracy study of the forward kinematics of planar 3-RPR parallel manipulators, Journal of Mechanical Design, 129(12), 2007, 1265–126810.1115/1.2779893Suche in Google Scholar
[28] Pedregosa F., Varoquaux G., Gramfort A., Michel V., Thirion B., Grisel O., Blondel M., Prettenhofer P., Weiss R., Dubourg V., Vanderplas J., Passos A., Cournapeau D., Brucher M., Perrot M., Duchesnay E., Scikit-learn: Machine Learning in Python, Journal of Machine Learning Research, 12, 2011, 2825–2830Suche in Google Scholar
[29] Gosselin C.M., Sefrioui J., Richard M.J., Solutions polynomiales au problème de la cinématique directe des manipulateurs parallèles plans à trois degrés de liberté, Mechanism and Machine Theory, 27(2), 1992, 107–11910.1016/0094-114X(92)90001-XSuche in Google Scholar
© 2020 Andrei Gorchakov et al., published by De Gruyter
This work is licensed under the Creative Commons Attribution 4.0 International License.
