ISSN 2071-8594

Russian academy of sciences

Editor-in-Chief

Gennady Osipov

N. V. Gridina, I. A. Еvdokimov, V. I. Solodovnikov Construction of hybrid neural networks using fuzzy logic elements

Abstract.

The issues of using fuzzy logic elements in the construction and training of hybrid neural networks for proceeding under conditions of uncertainty are considered. An embodiment of the fuzzy relations implementation and the fuzzy compositional output algorithm based on the neural network approach are presented. A neural network model of a fuzzy system is presented as a universal approximator, as well as the case while fuzziness appears at the learning stage.

Keywords:

hybrid neural network; fuzzy logic; fuzzy compositional neural networks.

PP. 91-97.

DOI 10.14357/20718594190209

References

1. Andrzej Piegat. Fuzzy modeling and control. Physica- Verlag HD, 2001. – pp.728
2. Khodashinskiy I.A., Malyutin N.D. 2015. Modeli staticheskikh iskusstvennykh neyronov [Models of static artificial neurons] // Obzor, Doklady TUSURa [Review, TUSUR reports], № 2 (36). pp. 100-107.
3. Borisov V.V., Kruglov V.V., Fedulov A.S. 2012. Nechetkiye modeli i seti. 2-ye izd., stereotip [Fuzzy models and networks. 2nd ed., Stereotype] — M.: Goryachaya liniya [Hotline]– Telekom. — 284 p.
4. Kruglov V.V., Dli M.I., Golunov R.YU. 2001. Nechetkaya logika i iskusstvennyye neyronnyye seti [Fuzzy logic and artificial neural networks] – M.: FIZMATLIT. - 201 p.
5. Rutkovskaya D., Pilin'skiy M., Rutkovskiy L. 2006. Neyronnyye seti, geneticheskiye algoritmy i nechetkiye sistemy [Neural networks, genetic algorithms and fuzzy systems]. M.: Goryachaya liniya [Hotline]–Telekom. — 452 p.
6. Osovskiy S. 2004. Neyronnyye seti dlya obrabotki informatsii [Neural networks for information processing] – M.: Finansy i statistika [Finance and Statistics]. – 344 p.