NEURAL NETWORKS MODULE

Authors

  • O. I. Chumachenko National Technical University of Ukraine “Ihor Sikorsky Kyiv Polytechnic Institute”
  • A. T. Kot National Technical University of Ukraine “Ihor Sikorsky Kyiv Polytechnic Institute”

DOI:

https://doi.org/10.18372/1990-5548.56.12937

Keywords:

Hybrid neural networks, Kohonnen neural network, perceptron, learning algorithm

Abstract

It is considered a basic approach for hybrid neuron network creation. As an example, the counter propagation neural network is analyzed. It is effectively used for image processing. Two modes of this neuron network functioning are considered. They are: accreditation and interpolation. Interpolation mode permits to reveal more complex features and can supply more precise results. Based on this analysis it is developed a new hybrid structure that includes Kohonnen neural network and perceptron. It is proposed a learning algorithm of this hybrid neuron network.

Author Biographies

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

Technical Cybernetic Department

Candidate of Science (Engineering). Assosiate Professor

A. T. Kot, National Technical University of Ukraine “Ihor Sikorsky Kyiv Polytechnic Institute”

Technical Cybernetic Department

Post-graduate student

References

V. V. Borisov, V. V. Kruglov, and A. S. Fedulov, Fuzzy models and networks. 2 nd ed., The stereotype. 2012. (in Russian)

Khaykin Saymon. Neural networks: full course, 2nd edition. 2006. (in Russian)

A. P. Rotshteyn, Intelligent identification technologies: fuzzy sets, neural networks, genetic algorithms. Monograph. Vinnitsa: "Universum-Vіnnitsya," 1999, 295 p. (in Russian)

J.-S. R. Jang, ANFIS: Adaptive-Network-Based Fuzzy Inference Systems, IEEE Trans. Systems, Man & Cybernetics 23 (1993).

Y. Bengio, A. Courville, and P. Vincent, Representation Learning: A Review and New Perspectives. Department of computer science and operations research, U. Montreal. 2014.

X. Glorot and Y. Bengio, Understanding the difficulty of training deep feedforward neural networks. 2010.

Downloads

Issue

Vol. 2 No. 56 (2018)

Section

COMPUTER-AIDED DESIGN SYSTEMS

License

Authors who publish with this journal agree to the following terms:

Authors retain copyright and grant the journal right of first publication with the work simultaneously licensed under a Creative Commons Attribution License that allows others to share the work with an acknowledgement of the work's authorship and initial publication in this journal.

Authors are able to enter into separate, additional contractual arrangements for the non-exclusive distribution of the journal's published version of the work (e.g., post it to an institutional repository or publish it in a book), with an acknowledgement of its initial publication in this journal.

Authors are permitted and encouraged to post their work online (e.g., in institutional repositories or on their website) prior to and during the submission process, as it can lead to productive exchanges, as well as earlier and greater citation of published work (See The Effect of Open Access).