Basic concepts of dynamic recurrent neural networks development

• Autorzy: Boyko N. , Pobereyko P.
• Języki publikacji: EN

Abstrakty

EN

In this work formulated relevance, set out an analytical review of existing approaches to the research recurrent neural networks (RNN) and defined precondition appearance a new direction in the field neuroinformatics – reservoir computing. Shows generalized classification neural network (NN) and briefly described main types dynamics and modes RNN. Described topology, structure and features of the model NN with different nonlinear functions and with possible areas of progress. Characterized and systematized wellknown learning methods RNN and conducted their classification by categories. Determined the place RNN with unsteady dynamics of other classes RNN. Deals with the main parameters and terminology, which used to describe models RNN. Briefly described practical implementation recurrent neural networks in different areas natural sciences and humanities, and outlines and systematized main deficiencies and the advantages of using different RNN. The systematization of known recurrent neural networks and methods of their study is performed and on this basis the generalized classification of neural networks was proposed.

Słowa kluczowe

EN

recurrent neural network; dynamic system; learning algorithms; reservoir computing; unsteady dynamics

• Wydawca: Polish Academy of Sciences, Branch in Lublin
• Czasopismo: ECONTECHMOD : An International Quarterly Journal on Economics of Technology and Modelling Processes
• Rocznik: 2016
• Tom: Vol. 5, No 2
• Strony: 63--68
• Opis fizyczny: Bibliogr. 20 poz., rys.

Twórcy

autor

Boyko N.

• Lviv Polytechnic National University

autor

Pobereyko P.

• Lviv Polytechnic National University

Bibliografia

• 1. Benderskaia E.N., Zhukova S.V. 2011. Neural network with chaotic dynamics in problems of cluster analysis, № 7, Рp. 74–86. (in Russian)
• 2. Benderskaya E.N., Zhukova S.V. 2013. Multidisciplinary Trends in Modern Artificial Intelligence: Turing’s Way // AIECM – Turing, Book Chapters: Artificial Intelligence, Evolutionary Computation and Metaheuristics, Springer, Рp. 320–343.
• 3. Coombes S. 2005. Waves, bumps, and patterns inneural field theories // Biological Cybernetics, Vol. 93, № 2, Рp. 91–108.
• 4. Dasgupta B., Siegelmann H., Sontag E.D. 1995. On the Complexity of Training Neural Networks with Continuous Activation Functions // IEEE Transactions on Neural Networks, 1995, Vol. 6, № 6, Рp. 1490–1504.
• 5. Dominey P.F. 1995. Complex sensory-motor sequence learning based on recurrent state representation and reinforcement learning // Biological Cybernetics, Vol. 73, № 3, Рp. 265–274.
• 6. Dunin-Barkowski W.L., Osovets N.B. 1995. HebbHopfield neural networks based on onedimensional sets of neuron states // Neural Processing Letters, Vol. 2, № 5, Рp. 28–31.
• 7. Feng J., Brown D. 1998. Fixed-point attractor analysis for a class of neurodynamics // Neural Computation, Vol. 10, Рp. 189–213.
• 8. Kaneko K. 2006. Life: an introduction to complex systems biology, Berlin: Springer-Verlag, p.369.
• 9. Maass W., Natschlдger T., Markram H. 2002. Real-time computing without stable states: a new framework for neural computations based on perturbations // Neural Computation, Vol. 11, Рp.2531–2560.
• 10. Schrauwen B., Verstraeten D., Campenhout J.V. 2007. An overview of reservoir computing theory, applications and implementations // Proc. of the 15th European Symp. on Artificial Neural Networks, Рp. 471–482.
• 11. Fedasyuk D., Yakovyna V., Serdyuk P., Nytrebych O. 2014. Variables state-based software usage model // Econtechmod : an international quarterly journal on economics in technology, new technologies and modelling processes, Lublin ; Rzeszow, Volum 3, number 2, Рp. 15-20.
• 12. Benderskaia E.N., Nikitin K.V. 2011. Modeling of neural activity in the brain, № 6-2(138), Рp. 34–40. (in Russian)
• 13. Rybytska O., Vovk M. 2014. An application of the fuzzy set theory and fuzzy logic to the problem of predicting the value of goods rests // Econtechmod : an international quarterly journal on economics in technology, new technologies and modeling processes, Lublin ; Rzeszow, Volum 3, №2, Рp. 65-69.
• 14. Benderskaia E.N. 2012. An opportunity to demonstrate some characteristics of the synchronization to identify self-organizing clusters in neural networks with chaotic dynamics, Рp. 69–73 (in Russian)
• 15. Magnitskii N.A., Sidorov S.V. 2004. New methods of chaotic dynamics, Moscow, p. 320 (in Russian)
• 16. Malinetskii G.G., Potapov A.B. 2006. Nonlinear dynamics in problems of cluster analysis, Moscow: KomKniga, p.240 (in Russian)
• 17. Piterson W., Weldon E. 1976. Error-correcting codes. Moscow: Мir publ., p.593 (in Russian)
• 18. Tiukin I.Iu., Terekhov V.A. 2008. Eshbі Vіlyam. 2006. Introduction to cybernetics. Мoscow, p.432. (in Russian)
• 19. Khaikin S. 2006. Neural networks – Moscow–St.- Petersburg– Kiev: ID “Vil’iams”, p.1103 (in Russian)
• 20. Benderskaya E.N. 2013. Nonlinear Trends in Modern Artificial Intelligence: A New Perspective // Beyond AI: Interdisciplinary Aspects of Artificial Intelligence. Topics in Intelligent Engineering and Informatics, Springer, Vol. 4., Рp. 113–124.

Uwagi

PL

Opracowanie ze środków MNiSW w ramach umowy 812/P-DUN/2016 na działalność upowszechniającą naukę