STRUCTURAL-PARAMETRIC SYNTHESIS OF THE FEEDFORWARD NEURAL NETWORKS WITH SIGMOID PIECEWISE-TYPE NEURONS

Authors

  • M. Z. Zgurovsky Rector of National Technical University of Ukraine “Ihor Sikorsky Kyiv Polytechnic Institute”
  • O. I. Chumachenko National Technical University of Ukraine “Ihor Sikorsky Kyiv Polytechnic Institute”
  • V. S. Gorbatiuk National Technical University of Ukraine “Ihor Sikorsky Kyiv Polytechnic Institute”

DOI:

https://doi.org/10.18372/1990-5548.58.13508

Keywords:

Feedforward neural networks, time series, sigmoid piecewise, training algorithm

Abstract

The method of structural and parametric synthesis of feedforward neural networks is considered, which includes Sigmoid Piecewise neurons, used in the process of a predictive model construction. The article describes the principles of a new developed Sigmoid Piecewise neuron constructing. It is proposed the method of structural and parametric synthesis with a single layer of  Sigmoid Piecewise neurons.The training algorithm of proposed neural networks is developed. The results of the effectiveness research of Sigmoid Piecewise neurons on real samples are presented.

Author Biographies

M. Z. Zgurovsky, Rector of National Technical University of Ukraine “Ihor Sikorsky Kyiv Polytechnic Institute”

Doctor of Engineering Science. Professor

Academician of the National Academy of Sciences of Ukraine

O. I. Chumachenko, National Technical University of Ukraine “Ihor Sikorsky Kyiv Polytechnic Institute”

Technical Cybernetic Department

Candidate of Science (Engineering). Assosiate Professor

V. S. Gorbatiuk, National Technical University of Ukraine “Ihor Sikorsky Kyiv Polytechnic Institute”

Technical Cybernetic Department

Post-graduate student

References

Jürgen Schmidhuber, “Deep learning in neural networks: An overview,” Neural networks, vol. 61, pp. 85–117, January 2015. doi.org/10.1016/j.neunet.2014.09.003

Nitish Srivastava, Geoffrey Hinton, Alex Krizhevsky, Ilya Sutskever, and Ruslan Salakhutdinov, “Dropout: A simple way to prevent neural networks from overfitting,” The Journal of Machine Learning Research, vol. 15, no. 1, pp. 1929–1958, 2014.

Olivier Delalleau, and Yoshua Bengio, “Shallow vs. deep sum-product networks,” Advances in Neural Information Processing Systems. 2011, pp. 666–674.

Stephen Boyd, and Lieven Vandenberghe, Convex optimization. Cambridge university press. 2004.

Martin Riedmiller, and Heinrich Braun, “A direct adaptive method for faster backpropagation learning: The RPROP algorithm,” IEEE International Conference on Neural Networks. 1993, pp. 586–591.

Hugo Larochelle, Yoshua Bengio, Jérôme Louradour, and Pascal Lamblin, “Exploring strategies for training deep neural networks,” Journal of machine learning research, 10, no., pp.1–40, Jan. 2009.

Donald F. Specht, “A general regression neural network,” IEEE transactions on neural networks 2, no. 6, 1991, pp. 568–576.

Sung-Kwun Oh, and Witold Pedrycz, “The design of self-organizing polynomial neural networks,” Information Sciences 141, no. 3–4, pp. 237–258, 2002.

Downloads

How to Cite

Zgurovsky, M. Z., Chumachenko, O. I., & Gorbatiuk, V. S. (2018). STRUCTURAL-PARAMETRIC SYNTHESIS OF THE FEEDFORWARD NEURAL NETWORKS WITH SIGMOID PIECEWISE-TYPE NEURONS. Electronics and Control Systems, 4(58), 42–47. https://doi.org/10.18372/1990-5548.58.13508

Issue

Vol. 4 No. 58 (2018)

Section

THEORY AND METHODS OF SIGNAL PROCESSING

License

The scientific journal “Electronics and control systems” adheres to the principles of Open Access and provides free, immediate, and permanent access to all published materials without financial, technical, or legal barriers for readers.

All articles are published in Open Access under the Creative Commons Attribution 4.0 International (CC BY 4.0) license.

Copyright

Authors who publish their works in the journal “Electronics and control systems”:

  • retain the copyright to their publications;

  • grant the journal the right of first publication of the article;

  • agree to the distribution of their materials under the CC BY 4.0 license;

  • have the right to reuse, archive, and distribute their works (including in institutional and subject repositories), provided that proper reference is made to the original publication in the journal.