Narzędzia help

Preferencje help
Widoczny [Schowaj] Abstrakt
Liczba wyników
first previous next last
cannonical link button


ECONTECHMOD : An International Quarterly Journal on Economics of Technology and Modelling Processes

Tytuł artykułu

Iterative method of neural elements synthesis with generalized threshold activation function

Autorzy Geche, F.  Batyuk, A.  Melnyk, O.  Spenyk, T. 
Treść / Zawartość
Warianty tytułu
Języki publikacji EN
EN Present work considers the neural elements (NE) with generalized threshold activation function and represents iterative method of their synthesis. Algorithm of vectors finding for structures of the neural elements with generalized threshold activation function was developed, and the sufficient condition of Boolean function unreliazability on such neural elements was discovered.
Słowa kluczowe
EN neural element   Boolean function   system of characters   structure vector   algorithm of synthesis  
Wydawca Polish Academy of Sciences, Branch in Lublin
Czasopismo ECONTECHMOD : An International Quarterly Journal on Economics of Technology and Modelling Processes
Rocznik 2015
Tom Vol. 4, No 4
Strony 37--42
Opis fizyczny Bibliogr. 29 poz., wz.
autor Geche, F.
autor Batyuk, A.
autor Melnyk, O.
  • Uzhhorod National University
autor Spenyk, T.
  • Lviv Polytechnic National University
1. Fukushima K. 1988. Neocognitron: A hierarchical neural network capable of visual pottern recognition. Neural Network (USA). Nr 1, 119-130.
2. Osovskiy S. 2002. Neural networks for information processing. Moscow: Finances and statistics. 345. (in Russian).
3. Geche F. E. and Anufriev A. V. 1990. Presentation and classification of images in threshold basis. Kiev: Cybernetics. Nr 5, 90-96. (in Russian).
4. Minaev Y., Filimonova O. and Benameur L. 2005. Methods and algorithms of tasks resolving related to identification and forecasting in conditions of uncertainty in neural network logical basis. Moscow: Hot line-Telecom. 205. (in Russian).
5. Zaychenko Y. P., Kelestin Y. V. and Sevaee Fatma. 2006. Comparative effectiveness analysis of indistinct neural networks in forecasting tasks in sphere of economics and finance. Kyiv: System investigations and information technologies. Nr 1, 100-110. (in Russian).
6. Geche F., Kotsovsky V., Batyuk A., Geche S. and Vashkeba M. 2015. Synthesis of Time Series Forecasting Scheme Based on Forecasting Models System. Lviv: Proceedings of the 11th International Conference «ICTERI 2015», 121-136.
7. Geche S. F. 2012. Forecasting of effectiveness evaluation indicators in usage of main assets of enterprise within neural basis. Uzhhorod: Scientific herald of Uzhhorod University. Series: Economics. Issue 3(37), 63-67. (in Ukrainian).
8. Bodyanskiy Ye. and Vynokurova O. 2011. Hybrid type-2 wavelet-neuro-fuzzy network for prediction of business processes. Wroclaw: Business Informatics. Nr 21, 9-21.
9. Rybytska O. and Vovk M. 2014. An application of the fuzzy set theory and fuzzy logic to the problem of predicting the value of goods rests. Lublin-Rzeszow: ECONTECHMOD. Vol.3, Nr 2, 65-69.
10. Gunasundari S. and Baskar S. 2009. Application of Artificial Neural Network in identification of lung diseases. Nature & Biologically Inspired Computing (IEEE). 1441–1444.
11. Bodyanskiy Ye., Kolchygin B. and Pliss I. 2011. Adaptive neuro-fuzzy Kohonen network with variable fuzzifier. Sofia: Int. J. Information Theories & Applications. Vol. 18, Nr 3, 215-223.
12. Komashinskiy V. I. and Smirnov D.A. 2002. Neural networks and their application in system of control and communication. Moscow: Hot line –Telecom. 96. (in Russian).
13. Lytvyn V., Semotuyk O. and Moroz O. 2013. Definition of the semantic metrics on the basis of thesaurus of subjects area. Lublin-Rzeszow: ECONTECHMOD. Vol. 2, Nr 4, 47-51.
14. Rozenblatt F. 1965. Principles of neural dynamics. Perceptrons and the theory of brain mechanisms. Moscow: World. 480. (in Russian).
15. Ayzenberh N. N. and Ivaskiv Y. L. 1977. Multilevel threshold logic. Kiev: Scientific mind. 145. (in Russian).
16. Aizenberg I. 2010. A Periodic Activation Function and a Modified Learning Algorithm for the Multi-Valued Neuron. IEEE Transaction on Neural Networks (IEEE). Vol. 21, Nr 12, 1939-1949.
17. Aizenberg I. 2011. Complex-Valued Neural Networks with Multi-Valued Neurons. Berlin-Heidelberg: Springer. 264.
18. Bodyanskiy Y. V., Kucherenko V. Y., Kucherenko Y. I., Mykhalyov O. I. and Filatov V. A. 2008. Hybrid neuro- phase models and multiagent technologies in complicated systems. Dnipropetrovsk: System technologies. 403. (in Ukrainian).
19. Tkachenko R. O. and Tsmots I. H. 1999. Accelerator for realization of artificial neural networks on the basis of neuroparadigm «Functionality on set of table functions». Kiev: Collection of scientific works of Institute of modeling problems in power engineering named after H.Y. Pukhova, National Academy of Sciences of Ukraine. Issue 7, 20-28. (in Ukrainian).
20. Khaykin S. 2006. Neural networks: complete course. Moscow: Williams-Telekom. 1104. (in Russian).
21. Geche F., Batyuk A., Kotsovsky V. and Gromaszek K. 2013. Synthesis of generalized neural elements using approximation method. Warszawa: Elektronika. Nr 8, 67-69.
22. Curtis Ch. and Rainer I., 1969. Theory of representation of final groups and associative algebras. Moscow: Science. 667. (in Russian).
23. Van der Waerden B. L. 1979. Algebra. Moscow: Science.623. (in Russian).
24. Holubov B. I., Efimov A. V. and Skvortsov V. A. 1987. Walsh series and transforms. Theory and application. Moscow: Science. 343. (in Russian).
25. Kharmut Kh. 1975. Transmission of information by orthogonal functions. Moscow: Connectivity. 267. (in Russian).
26. Trakhtman A. M. and Trakhtman V. A. 1975. Fundamentals of theory of discrete signals on finite intervals. Moscow: Soviet Radio.177. (in Russian).
27. Arutyunyan F. H. and Talalyan A. A. 1964. On the uniqueness of series in the Haar and Walsh systems. Moscow: Herald of Academy of Sciences of USSR. Series: Mathematics. Vol. 28, Nr 6, 1391-1408. (in Russian).
28. Dertouzos M. 1967. The threshold logic. Moscow: World. 342. (in Russian).
29. Geche F. E. 1998. Implementation of Boolean function on one neural element and adders by mod 2. Lviv: Information technologies and systems. Vol. 1, Nr 1/2, 105-109. (in Russian).
Kolekcja BazTech
Identyfikator YADDA bwmeta1.element.baztech-c670128f-ad35-40ad-9c32-cd71f774c87d