HYBRID NEURON NETWORKS BASED ON RADIAL BASIS NETWORK WITH DIFFERENT RADIAL BASIS FUNCTION

Authors

  • O. I. Chumachenko National Technical University of Ukraine “Igor Sikorsky Kyiv Polytechnic Institute”
  • S. T. Dychko National Technical University of Ukraine “Igor Sikorsky Kyiv Polytechnic Institute”
  • А. R. Rizhiy National Technical University of Ukraine “Igor Sikorsky Kyiv Polytechnic Institute”

DOI:

https://doi.org/10.18372/1990-5548.63.14516

Keywords:

Hybrid neural network, structural-parametric synthesis, optimization problem

Abstract

It is considered the problem of structural-parametric synthesis of a hybrid neural networks based on the use of radial basis network. Hybridization is achieved through the use of various radial basis functions: Gaussian, multivariate, inverse quadratic, inverse multivariate, thin plate spline, linear, cubic, wavelet functions. The problem of structural-parametric synthesis of hybrid neural network consists in the optimal choice of the number of layers, the number of neurons in the layers, the order of alternation of layers with different neurons. The problem of optimal choice of the number of network cascades and the type of radial basis function in each cascade of the number of layers is solved. Examples of a hybrid neural network synthesis using this methodology for classification and prediction tasks solution are given.

Author Biographies

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

Technical Cybernetic Department

Doctor of Engineering Science. Associate Professor

orcid.org/0000-0003-3006-7460

S. T. Dychko, National Technical University of Ukraine “Igor Sikorsky Kyiv Polytechnic Institute”

Technical Cybernetic Department

Bachelor

А. R. Rizhiy, National Technical University of Ukraine “Igor Sikorsky Kyiv Polytechnic Institute”

Technical Cybernetic Department

Bachelor

References

Ye. Bodyanskiy and O. Vynokurova, “Compartmental adaptive wavelon and its learning algorithm,” Control systems and computers 1, pp 47–53, 2009.

O. I. Chumachenko, S. T. Dychko and A. R. Rizhiy, “Hybrid Neuron Networks Based on Q-, W- and Classical Neurons,” Electronics and Control Systems, pp. 58–62, 2019. https://doi.org/10.18372/1990-5548.62.14385

Ye. Bodyanskiy, I. Pliss, O. Vynokurova, “Hybrid GMDH-neural network of computational intelligence,” Proc. 3rd International Workshop on Inductive Modelling, Poland, Krynica. 2009, рр. 100–107.

Ye. Bodyanskiy, O. Vynokurova, and N. Teslenko, “Cascade GMDH-Wavelet-Neuro-Fuzzy Network,” The 4th International Workshop on Inductive ModellingIWIM 2011, рр. 22–30.

Е. А. Vinokurova, “Generalized multidimensional wavelet-neuro-fuzzy system in computational intelligence problems,” Intelligent decision-making systems and problems of computational intelligence: a collection of scientific papers based on the materials of an international scientific conference. Evpatoriay–Cherson, vol. 2, 2010, pp. 329–333.

E. Zitzler, M. Laumanns and L. Thiele, “SPEA2: Improving the Strength Pareto approach,” Swiss Federal Institute Technology, 2001.

Optical Recognition of Handwritten Digits Data Set [Online]. Avaible: https://archive.ics.uci.edu/ml/datasets/Optical+Recognition+of+Handwritten+Digits

Daily Minimum Temperatures In Melbourne [Online]. Avaible: https://www.kaggle.com/paulbrabban/daily-minimum-temperatures-in-melbourne

Downloads

How to Cite

Chumachenko, O. I., Dychko, S. T., & Rizhiy А. R. (2020). HYBRID NEURON NETWORKS BASED ON RADIAL BASIS NETWORK WITH DIFFERENT RADIAL BASIS FUNCTION. Electronics and Control Systems, 1(63), 32–36. https://doi.org/10.18372/1990-5548.63.14516

Issue

Vol. 1 No. 63 (2020)

Section

COMPUTER ENGINEERING

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.