PL EN


Preferencje help
Widoczny [Schowaj] Abstrakt
Liczba wyników
Tytuł artykułu

Convolutional neural networks training for autonomous robotics

Treść / Zawartość
Identyfikatory
Warianty tytułu
Języki publikacji
EN
Abstrakty
EN
The article discusses methods for accelerating the operation of convolutional neural networks for autonomous robotics learning. The analysis of the theoretical possibility of modifying the neural network learning mechanism is carried out. Classic semiotic analysis and the theory of neural networks is proposed to union. An assumption is made about the possibility of using the symmetry mechanism to accelerate the training of convolutional neural networks. A multilayer neural network to represent how space is an attempt has been made. The conclusion was based on the laws on the plane obtained earlier. The derivation of formulas turned out to be impossible due to the problems of modern mathematics. A new approach is proposed, which involves combining the gradient descent algorithm and the stochastic completion of convolutional filters by the principles of symmetries. The identified algorithms allow increasing the learning rate from 5% to 15%, depending on the problem that the neural network solves.
Wydawca
Rocznik
Tom
Strony
75--79
Opis fizyczny
Bibliogr. 28 poz., rys.
Twórcy
  • Kalashnikov Izhevsk State Technical University Institute of Informatics and Hardware Software department Student Street, 7, Izhevsk, Russia
  • Slovak University of Technology Faculty of Materials Science and Technology Institute of Production Technologies J. Bottu 25, 917 24 Trnava, Slovak Republic
autor
  • Kalashnikov Izhevsk State Technical University Institute of Informatics and Hardware Software department Student Street, 7, Izhevsk, Russia
Bibliografia
  • [1] P. Bozek, Z. Ivandic and others. “Solutions to the characteristic equation for industrial robot's elliptic trajectories”. Tehnicki Vjestnik – Technical Gazette, vol. 23, pp. 1017-1023, 2016.
  • [2] A. Kilin, P. Bozek, and others. “Experimental investigations of a highly maneuverable mobile omniwheel robot“. International Journal of Advanced Robotic Systems. Vol. 14, iss. 6 (2017), pp. 1-9.
  • [3] R. Pirnik, M. Hruboš and others. “Integration of inertial sensor data into control of the mobile platform”. in Advances in Intelligent and Soft Computing, SDOT 2015, vol. 511, pp. 271-282.
  • [4] T. Dodok, N. Cubonova and others. “Utilization of strategies to generate and optimize machining sequences in CAD/CAM“. 12th International Scientific Conference of Young Scientists on Sustainable, Modern and Safe Transport. Procedia Engineering. Volume: 192, pp. 113- 118.
  • [5] M. Saga, M. Vasko and others. Chosen numerical algorithms for interval finite element analysis. Modelling of Mechanical and Mechatronic Systems. Procedia
  • [6] J. Peterka, P. Pokorny and S. Vaclav. CAM strategies and surface accuracy. Annals of DAAAM and Proceedings. 2008, pp. 1061-1062.
  • [7] M. Beno, M. Zvoncan and others. Circular interpolation and positioning accuracy deviation measurement on five axis machine tools with different structures. Tehnicki Vjestnik – Technical Gazette. 2013, 20, 3, pp. 479-484.
  • [8] A. Nemethova, D. Borkin and G. Michalconok. Comparison of Methods for Time Series Data Analysis for Further Use of Machine Learning Algorithms. In Proceedings of the Computational Methods in Systems and Software. Springer, Cham, 2019. pp. 90-99.
  • [9] M. Nemeth, A. Nemthova and G. Michalconok. Determination issues of data mining process of failures in the production systems. Book Series: Advance in Intelligent Systems and Computing. 2019. Vol 985, pp. 200-207.
  • [10] A. Nemethova, M. Nemeth and others. Identification of KDD problems from medical data. Series: Advance in Intelligent Systems and Computing. 2019. Vol 985, pp. 191-199.
  • [11] P. Anderson, P. Culley and T.J. Parker. Marketing Research. London: Hansen Publisher, 2003.
  • [12] D.G. Smith and R.G. Rhodes. “Specification Formulation”. Journal of Engineering, December 2001, Vol. 2, No. 2. pp. 223-228.
  • [13] V.I. Arnol′d. “On funcWons of three variables”. Amer. Math. Soc. Transl. (2) 28, 1963, pp. 51-54.
  • [14] R. Rigamonti, A. Sironi, and others. “Learning separable filters”. In Conference on Computer Vision and Pattern Recogonition (CVPR), 2013.
  • [15] T. Krenicky. “Implementation of Virtual Instrumentation for Machinery Monitoring”. Scientific Papers: Operation and Diagnostics of Machines and Production Systems Operational States: Vol. 4. RAM-Verlag, Lüdenscheid, 2011, pp. 5-8. ISBN 978-3-942303-10-1.
  • [16] Z. Murcinkova and T. Krenicky. “Implementation of virtual instrumentation for multiparametric technical system monitoring”. SGEM 2013: 13th Int. Multidisciplinary Sci. Geoconf. Vol. 1. 16-22 June, 2013, Albena, Bulgaria. Sofia: STEF92 Technology, 2013. pp. 139-144. ISBN 978-954- 91818-9-0.
  • [17] S. Anwar, K. Hwang, and W. Sung. “Fixed point optimization of deep convolutional neural networks for object recognition”. In Acoustics, Speech, and Signal Processing (ICASSP), International Conference on, 2015.
  • [18] G. Huang, Y. Sun and others. “Deep networks with stochastic depth”. in European Conference on Computer Vision (ECCV), 2016.
  • [19] V.I. Arnol′d. "On funcWons of three variables." In Amer. Math. Soc. Transl. 1963, Vol. 28, No.2. pp. 51-54.
  • [20] G.E. Hinton, O. Vinyals and J. Dean. “Distilling the knowledge in a neural network”. NIPS Deep Learning Workshop, 2014.
  • [21] P. Bozek, A. Lozhkin, and others. “Information technology and pragmatic analysis”. Computing and informatics. 2018. Vol. 37, Issue 4, С, pp. 1011-1036
  • [22] A. Lozhkin, A. Korobeynikov and R. Khaziyakhmetov "The Newton problem solution of the transformed complex curve parameters". In Journal of Physics: Conference Series, 2019, Vol. 1399, Applied Physics, doi:10.1088/1742- 6596/1399/2/022004.
  • [23] Y. Goodfellow, A. Bengio and A. Courville. “Deep Learning”. The MIT Press, 2016, pp. 84-91
  • [24] P. Bozek and E. Pivarciova. “Registration of Holographic Images Based on Integral Transformation”. Computing and Informatics. Vol. 31, No. 6 (2012), pp. 1369-1383.
  • [25] P. Bozek and G. Chmelikova. “Virtual Technology Utilization in Teaching“. ICL 2011, 14th International Conference on Interactive Collaborative Learning and 11th International Conference Virtual University. Piscataway: IEEE, 2011, pp. 409-413.
  • [26] J. Zhao. “Exponential stabilization of memristor-based neural networks with unbounded time-varying delays“. Science China Information Sciences, Volume 64, Issue 8, 1 August 2021,
  • [27] S. Ivanovna. “Neural Network Modeling of Productive Intellectual Activity in Older Adolescents“. Advances in Intelligent Systems and Computing, Volume 1250, IntelliSys 2020, London; United Kingdom; pp. 399-406.
  • [28] Z. Murcinkova and T. Krenicky. “Applications utilizing the damping of composite microstructures for mechanisms of production machines and manipulator devices”. SGEM 2013: 13th Int. Multidisciplinary Sci. Geoconf. Vol. 1. 16-22 June, 2013, Albena, Bulgaria. Sofia: STEF92 Technology, 2013. pp. 23-30. ISBN 978-954-91818-9-0.
Uwagi
Opracowanie rekordu ze środków MNiSW, umowa Nr 461252 w ramach programu "Społeczna odpowiedzialność nauki" - moduł: Popularyzacja nauki i promocja sportu (2021).
Typ dokumentu
Bibliografia
Identyfikator YADDA
bwmeta1.element.baztech-17406c08-5666-42a1-ab87-b4f265937c76
JavaScript jest wyłączony w Twojej przeglądarce internetowej. Włącz go, a następnie odśwież stronę, aby móc w pełni z niej korzystać.