Neural networks module learning

Authors

  • O. I. Chumachenko National Technical University of Ukraine “Kyiv Polytechnic Institute”
  • I. V. Kryvenko Nаtiοnаl Аviаtiοn Univеrsitу

DOI:

https://doi.org/10.18372/1990-5548.48.11212

Keywords:

Artificial intelligence, connectionist models, bidirectional associative memory

Abstract

Currently, there exists a huge number of neural networks of different classes, each with itsown advantages and disadvantage. However, there aren’t a lot of focus on hybrid neural networks, basedon the combination of knowт topologies of neural networks. Modular organization principle seems to bevery promising, however principles of its module creation isn’t known and needs further research. Thepresent study, therefore, proposes some methods of hybrid neural network module creation and theirlearning algorithms

Author Biographies

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

Candidate of engineering. Associate Professor.Technical Cybernetic Department

I. V. Kryvenko, Nаtiοnаl Аviаtiοn Univеrsitу

Bachelor. Аviаtiοn Сοmputеr-Intеgrаtеd Сοmplеxеs Dеpаrtmеnt

References

D. Yu. Koval, G. A. Sipakov, and D. D. Shevchuk, “Using ANFIS and NEFCLASS neurаl networks in classification problems”. Electronics and Control Systems, no. 1(43), Kyiv, NAU, pp. 93–98, 2015.

С. Tremblay, N. Berberian, and S. Chartier, Didirectional Associative Memory for Short-term Memory Learning, COGSCI, 2014, pp.1–6.

S. Chartier, and M. Boukadoum, “Encoding static and temporal patterns with a bidirectional heteroassociative memory”. Journal of Applied Mathematics, pp. 1–34, 2011.

S. Chartier, and M. Boukadoum, “A bidirectional heteroassociative memory for binary and grey-level patterns”. IEEE Transactions on Neural Networks, vol. 17(2), 2006, pp. 385–396.

Downloads

Issue

Section

COMPUTER-AIDED DESIGN SYSTEMS