Modeling of effect of topological structure on characteristics of spike neural network

Authors

  • Анатолій Антонович Шиян Vinnitsa National Technical University Khmelnitskoe shosse 95, Vinnitsa, 21021, Ukraine, Ukraine
  • Вікторія Сергіївна Іваненко Vinnitsa National Technical University Khmelnitskoe shosse 95, Vinnitsa, 21021, Ukraine, Ukraine

DOI:

https://doi.org/10.15587/1729-4061.2013.14675

Keywords:

Spike, neural network, topology, way, data processing, distribution, receptor motoneuron

Abstract

Despite the active study of the spike neural networks, little attention has been paid to the effect of the topological organization of such networks on the efficiency of information transformation. This article proposed an approach to modeling the effects of the neural network topology on the behavior of a spike neuron, which makes it possible to evaluate the effectiveness of information transformation. To do this, the notion of a set of ways of distribution of spike signal through the neural network was introduced. The models are constructed to describe the effect of the neural network topology on a detached neuron for the two cases. It was shown that the spike neural network has both minimum and maximum sizes, which depend on the characteristics of the network, as well as on the specificity of the operation of the spike neuron. The results provide new ways for explaining the functioning of the natural neural networks and for building the effective artificial neural networks (e.g. for pattern recognition, or for managing technical objects)

Author Biographies

Анатолій Антонович Шиян, Vinnitsa National Technical University Khmelnitskoe shosse 95, Vinnitsa, 21021, Ukraine

Associate Professor

Department of Computer Science

Вікторія Сергіївна Іваненко, Vinnitsa National Technical University Khmelnitskoe shosse 95, Vinnitsa, 21021, Ukraine

Student

Department of Metrology and Industrial Automatics

References

  1. Осипов Г. В. Синхронизация при обработке и передаче информации в нейронных сетях [Текст] / Г. В. Осипов. – Нижний Новгород : ННГУ, 2007. – 99 с.
  2. Брюхомицкий Ю. А. Нейросетевые модели для систем информационной безопасности [Текст] / Ю. А. Брюхомицкий. – Таганрог: Изд-во ТРТУ, 2005. – 160 с.
  3. Pavlov A. N. Wavelet analysis in neurodynamics [Текст] / A. N. Pavlov, A. A. Koronovskii, A. A. Ovchinnikov et al. // Uspekhi Fizicheskikh Nauk. – 2012. Vol. 182, No 9. – Р. 905-939.
  4. Tapson J. Synthesis of neural networks for spatio-temporal spike pattern recognition and processing [Текст] / J. Tapson, G. Cohen, S. Afshar et al. – Доступно за адресою: http://arxiv.org/abs/1304.7118. 26 квітня 2013. – 21 р.
  5. Sinyavskiy O. Y. Reinforcement learning of a spiking neural network in the task of control of an agent in a virtual discrete environment [Текст] / O. Y. Sinyavskiy, A. I. Kobrin // Rus. J. Nonlin. Dyn. – 2011. – Vol. 7, No. 4 (Mobile Robots). – Р. 859–875.
  6. Sinyavskiy O. Y. Generalized stochastic spiking neuron model and extended Spike Response Model in spatial-temporal impulse pattern detection task [Текст] / O. Y. Sinyavskiy, A. I. Kobrin // Optical Memory & Neural Networks (Information Optics). – 2010. – Vol. 19, No 4. – P. 300-309.
  7. Medvedev G. S. The geometry of spontaneous spiking in neuronal networks [Текст] / G. S. Medvedev, S. Zhuravytska // Journal of Nonlinear Science. – 2012. – Vol. 22, Issue 5. – Р. 689-725.
  8. Huang, G. B. Extreme learning machine: Theory and applications [Текст] / G. B. Huang, Q. Y. Zhu, C. K. Siew. // Neurocomputing. – 2006. – Vol. 70. – Р. 489–501.
  9. Дубровин Б. А. Современная геометрия [Текст] / Б. А. Дубровин, С. П. Новиков, А. Т. Фоменко. – М.: Наука, 1979. – 760 с.
  10. Nicholls J. G. From Neuron to Brain [Текст] / J. G. Nicholls, A. R. Martin, B. G. Wallace, P. A. Fuchs. – Sunderland : Sinauer Associates, Inc., 2001. – 672 p.
  11. Osipov, H. V. (2007). Sinkhronozatsia pri obrabotke i peredache informatsii v neirinnikh setiakh. Nizhnii Novhorod : NNHU.
  12. Briukhomitskii, Yu. A. (2005). Neirosetevie mideli dlia system informatsionnoi bezopasnosti. Tahanroh: TRTU.
  13. Pavlov, A. N., Koronovskii, A. A., Ovchinnikov, A. A., et al. (2012). Wavelet analysis in neurodynamics. Uspekhi Fizicheskikh Nauk, 182(9), 905-939.
  14. Tapson, J., Cohen, G., Afshar, S., et al. (2013). Synthesis of neural networks for spatio-temporal spike pattern recognition and processing. – Available at SRRN: http://arxiv.org/abs/1304.7118 .
  15. Sinyavskiy, O. Y., & Kobrin, A. I. (2011). Reinforcement learning of a spiking neural network in the task of control of an agent in a virtual discrete environment. Rus. J. Nonlin. Dyn., Vol. 7(4) (Mobile Robots), 859–875.
  16. Sinyavskiy, O. Y., & Kobrin, A. I. (2010). Generalized stochastic spiking neuron model and extended Spike Response Model in spatial-temporal impulse pattern detection task. Optical Memory & Neural Networks (Information Optics), Vol. 19(4), 300-309.
  17. Medvedev, G. S., & Zhuravytska, S. (2012). The geometry of spontaneous spiking in neuronal networks. Journal of Nonlinear Science, Vol. 22(4), 689-725.
  18. Huang, G. B., Zhu, Q. Y., & Siew, C. K. (2006). Extreme learning machine: Theory and applications. Neurocomputing, Vol.70, 489–501
  19. Dubrovin, B. A., Novikov, S. P., & Fomenko A. T. (1979). Sovremennaia geometria. Moscow, USSR : Nauka.
  20. Nicholls, J. G., Martin, A. R., Wallace, B. G., & Fuchs, P. A. (2001). From Neuron to Brain. – Sunderland : Sinauer Associates, Inc.

Downloads

Published

2013-06-20

How to Cite

Шиян, А. А., & Іваненко, В. С. (2013). Modeling of effect of topological structure on characteristics of spike neural network. Eastern-European Journal of Enterprise Technologies, 3(3(63), 19–21. https://doi.org/10.15587/1729-4061.2013.14675

Issue

Vol. 3 No. 3(63) (2013): Control systems

Section

Control systems

License

Copyright (c) 2014 Анатолій Антонович Шиян, Вікторія Сергіївна Іваненко

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.