Recurrent approximation as the tool for expansion of functions and modes of operation of neural network

Authors

  • Alexander Trunov Petro Mohyla Black Sea State University 68 Marines str., 10, Mykolaiv, Ukraine, 54000, Ukraine

DOI:

https://doi.org/10.15587/1729-4061.2016.81298

Keywords:

рекурентна мережа, режими роботи, продуктивні правила, аналітичне навчання нейрону, оцінка похибки, координаційне управління

Abstract

The paper considers the role of recurrent artificial neural network (RANN) for the solution of specific problems of coordination control, the relevance of which is predetermined by the development of modern automated systems. We synthesized the RANN information processing structure that is formed based on the indicators - vectors and recurrent approximation of continuous function. New modes of its work and expanded functionality were examined. It was demonstrated that it is capable to implement zero correction modes, calibration, preparing information on the error of approximation, to solve the problem of minimization and act as a module of decision making support system.

We proposed generalized algorithm for analytical determination of synaptic weights coefficients and evaluation of their error. It is shown that the application of the indicator vectors makes these algorithms practically independent of selecting initial approximation of synaptic weights coefficients, while the network acquires mechanism of readjustment during optimal control. For its implementation, depending on the changes that occur to the object, in accordance with the obtained analytical criteria of evaluation of error of synaptic weights coefficients, their readjustment is conducted. The synthesized structure is able to realize algorithms that provide a necessary set of operating modes and formation of productive or controlling rules based on the analysis of behavior of the set of the indicator vectors. Its structure forms the information support of the conditional part of the rules "condition–action" and implements effective part in the algorithms of coordination control. It also is capable to implement simple algorithms for finding roots and control that minimizes or maximizes continuous function or the Lagrange function under conditions of existence of restrictions of inequalities for a nonlinear object.

The application of the obtained results is also useful for solving various separate problems: formation of productive rules for solving the problems of finding simple root of monotonic function, finding a not simple root of monotonic function, finding a root of oscillating function, selecting controlling influence and the problem on the synthesis of controlling influence. Obtained results continue and complement practical implementation of the idea of recurrent approximation for solving the tasks of modeling and design.

Author Biography

Alexander Trunov, Petro Mohyla Black Sea State University 68 Marines str., 10, Mykolaiv, Ukraine, 54000

PhD, Associate Professor, First Vice-Rector

Department of automation and computer-integrated technologies

References

  1. Petrov, E. Gh. (2014). Koordynacyonnoe upravlenye (menedzhment) processamy realyzacyy reshenyj. Problems of Information Technology, 02 (016), 6–11.
  2. Khodakov, V. E. (2014). O razvyty osnov teoryy koordynacyy slozhnykh system. Problems of Information Technology, 02 (016), 12–22.
  3. Fisun, M. T. (2015). Modeljuvannja dynamichnykh procesiv vitrovoji elektrychnoji stanciji u seredovyshhi gpss. Problems of Information Technology, 01 (017), 145–149.
  4. Вodyanskiy, Ye., Chaplanov, O., Popov, S. (2003). Adaptive prediction of quasiharmonic sequences using feedforward network. Proc. Int. Conf. Artificial Neural Networks and Neural Information Processing ICANN, 378–381.
  5. Kryuchkovskiy, V. V., Petrov, K. E. (2011). Development of methodology for identification models of intellectual activity. Problems of information technology, 9, 26–33.
  6. Кhodakov, V. E. (2013). Kharakternye osobennosti odnogo klassa sotsial'no-ekonomicheskikh sistem. Problems of Information Technology, 2 (014), 10–14.
  7. Kovalenko, Y. Y. (2015). Sravnyteljnyj analyz metodov klasyfykacyy v avtomatyzovanykh systemakh tekhnychekoj dyaghnostyky. Problems of Information Technology, 01 (017), 37–41.
  8. Kravecj, I. O. (2015). Vykorystannja nechitkykh nejronnykh merezh dlja identyfikaciji ta keruvannja slaboformalizovannymy ob'jektamy. Problems of Information Technology, 01 (017), 150–154.
  9. Kryvulja, Gh. V. (2015). Ekspertnaja systema funkcionaljnogho diaghnostyrovanyja tekhnycheskykh obektov s nejronechetkoj bazoj danykh. Problems of Information Technology, 01 (017), 29–36.
  10. Ghavrylenko, V. O. (2015). Zastosuvannja metodiv nechitkoji loghiky dlja kontrolju stanu zernovogho nasypu v zernoskhovyshhakh. Problems of Information Technology, 01 (017), 77–82.
  11. Dzjuba, D. A. (2011). Prymenenye metoda kontrolyruemogho vozmushhenyja dlja modyfykacyy nejrokontrolerov vrealjnom vremeny. Matematychny mashyny y systemy, 1, 20–28.
  12. Kondratenko, Y. P. (2012). Correction of the Knowledge Database of Fuzzy Decision Support System with Variable Structure of the Input Data. Modeling and Simulation: Proc. of the Int. Conference MS'12, 56–61.
  13. Kondratenko, Y. P., Korobko, V. V., Korobko, O. V. (2013). Distributed computer system for monitoring and control of thermoacoustic processes. 2013 IEEE 7th International Conference on Intelligent Data Acquisition and Advanced Computing Systems (IDAACS), 249–253. doi: 10.1109/idaacs.2013.6662682
  14. Kondratenko, Y. P., Klymenko, L. P., Kondratenko, V. Y., Kondratenko, G. V., Shvets, E. A. (2013). Slip displacement sensors for intelligent robots: Solutions and models. 2013 IEEE 7th International Conference on Intelligent Data Acquisition and Advanced Computing Systems (IDAACS), 861–866. doi: 10.1109/idaacs.2013.6663050
  15. Trunov, A. N. (2011). Recurrence approximation in problems of modeling and design. Petro Mohyla BSSU, 272.
  16. Trunov, A. N. (2013). Intellectualization of the models’ transformation process to the recurrent sequence: European Applied Sciences, 9 (1), 123–130.
  17. Trunov, A. (2014). Application of the recurrent approximation method to synthesis of neuron net for determination the hydrodynamic characteristics of underwater vehicles: Problem of Information Technology, 02 (016), 39–47.
  18. Trunov, A. (2016). Vector indicator as a tool of recurrent artificial neuron net for processing data. EUREKA: Physics and Engineering, 4 (5), 55–60. doi: 10.21303/2461-4262.2016.000129
  19. Khajkyn, S. (2006). Nejronnye sety: polnyj kurs. 2nd edition. Moscow.: yzd. Dom «Vyljjams», 1104.
  20. Chebotarev, P. Y., Agaev, R. P. (2009). Coordination in multiagent systems and Laplacian spectra of digraphs. Automation and Remote Control, 70 (3), 469–483. doi: 10.1134/s0005117909030126
  21. Usjkov, A. A., Kuzjmyn, A. V. (2004). Yntellektualjnye tekhnologhyy upravlenyja: yskusstvennye nejronnye sety y nechetkaja loghyka. Moscow: Ghorjachaja lynyja – Telekom, 143.
  22. Rutkovskaja, D., Pylynjskyj, M., Rutkovskyj, L. (2004). Nejronnye sety, ghenetycheskye alghorytmy y nechetkye systemy. Moscow: Ghorjachaja lynyja – Telekom, 452.
  23. HuH, D., Todorov, E. (2009). Real-time motor control using recurrent neural networks. 2009 IEEE Symposium on Adaptive Dynamic Programming and Reinforcement Learning. doi: 10.1109/adprl.2009.4927524
  24. Ioffe, S., Szegedy, C. (2015). Batch normalization: Accelerating deep network training by reducing internal covariate shift. Available at: https://arxiv.org/abs/1502.03167v3

Downloads

Published

2016-10-30

How to Cite

Trunov, A. (2016). Recurrent approximation as the tool for expansion of functions and modes of operation of neural network. Eastern-European Journal of Enterprise Technologies, 5(4 (83), 41–48. https://doi.org/10.15587/1729-4061.2016.81298

Issue

Vol. 5 No. 4 (83) (2016): Mathematics and Cybernetics - applied aspects

Section

Mathematics and Cybernetics - applied aspects

License

Copyright (c) 2016 Alexander Trunov

Creative Commons License

This work is licensed under a Creative Commons Attribution 4.0 International License.

The consolidation and conditions for the transfer of copyright (identification of authorship) is carried out in the License Agreement. In particular, the authors reserve the right to the authorship of their manuscript and transfer the first publication of this work to the journal under the terms of the Creative Commons CC BY license. At the same time, they have the right to conclude on their own additional agreements concerning the non-exclusive distribution of the work in the form in which it was published by this journal, but provided that the link to the first publication of the article in this journal is preserved.

A license agreement is a document in which the author warrants that he/she owns all copyright for the work (manuscript, article, etc.).
The authors, signing the License Agreement with TECHNOLOGY CENTER PC, have all rights to the further use of their work, provided that they link to our edition in which the work was published.
According to the terms of the License Agreement, the Publisher TECHNOLOGY CENTER PC does not take away your copyrights and receives permission from the authors to use and dissemination of the publication through the world's scientific resources (own electronic resources, scientometric databases, repositories, libraries, etc.).
In the absence of a signed License Agreement or in the absence of this agreement of identifiers allowing to identify the identity of the author, the editors have no right to work with the manuscript.
It is important to remember that there is another type of agreement between authors and publishers – when copyright is transferred from the authors to the publisher. In this case, the authors lose ownership of their work and may not use it in any way.