On the Equivalence of Real Dynamic Process and Its Neural Network Quadratic Models

Vasiliy Ye. Belozyorov, Danylo V. Dantsev, Yevhen V. Koshel

Анотація


A dynamic process defined by its own time series is considered. Using the methods of qualitative recurrent analysis, the dimension of the embedding space and the optimal time delay of the specified series are determined. Using these characteristics, a neural network with a quadratic activation function is modeled. The simulation result is presented in the form of a system of neural ODEs. After that, the Lyapunov exponents of the real dynamic system and its neural network model are calculated. Then the closeness of these exponents for a real system and its model makes it possible to judge the adequacy (equivalence) of both dynamic processes. Examples are given.


Ключові слова


system of ordinary autonomous differential equations; quadratic activation function; neural network; Lyapunov exponents

Повний текст:

PDF (English)

Посилання


V. Ye. Belozyorov, D. V. Dantsev, S. A. Volkova, On equivalence of linear control systems and its usage to verification of the adequacy of different models for a real dynamic process, Journal of Optimization, Differential Equations and Their Applications (JODEA), 28(1)(2020), 43–97.

V. Ye. Belozyorov, D. V. Dantsev, Stability of neural ordinary differential equations with power nonlinearities, Journal of Optimization, Differential Equations and Their Applications (JODEA), 28(2)(2020), 21–46.

V. Ye. Belozyorov, O. V. Pohorielov, V. N. Serdiuk, V. G. Zaytsev, New approach to problem of diagnostics of cerebral cortex diseases using chaotic dynamics methods, In: The collection of 7 th The international conference "Social Science and Humanity", September 23 – 29, London, 2(2017), 7–28.

R. Brown, P. Bryant, H. D. I. Abarbanel, Computing the Lyapunov spectrum of a dynamical system from an observed time series, Physical Review A, 43(1991), 2787–2806.

H. F. Bremen, F. E. Udwadia, W. Proskurowski, An efficient QR based method for the computation of Lyapunov exponents, Physica D: Nonlinear Phenomena, 101(1997), 1–16.

R. T. Q. Chen, Y. Rubanova, J. Bettencourt, D. Duvenaud, Neural ordinary differential equations, arXiv preprint arXiv:1806.07366v5[cs.LG], (2019), 1–18.

F. Christiansen, H. H. Rugh, Computing Lyapunov spectra with continuous Gram-Schmidt orthonormalization, arXiv:chao-dyn/9611014v1, (1996), 1–14.

F. R. Gantmacher, The Theory of Matrices, AMS Chelsea Publising, Providence, Rhode Island, 2000.

S. Haykin, Neural Networks. A Comprehensive Foundation, Second Edition, Pearson Education, Prentice Hall, 2005.

Y. V. Koshel, Local jacobian estimation for delay embedded time series data, In: The abstracts of 18th international scientific and practical conference "MPZIS – 2021", November 17 – 19, Dnipro, (2021), 152–153.

H. K. Khalil, Nonlinear Systems – 2nd Edition, (Prentice Hall/New-Jersy), 1996.

Q. Li, P. Xu, Estimation of Lyapunov spectrum and model selection for a chaotic time series, Applied Mathematical Modelling, 36(2012), 6090– 6099.

Z. Liu, Chaotic time series analysis, Mathematical Problems in Engineering, 2010 (2010), 720190, 1–31.

G. Teschi, Ordinary Differential Equations and Dynamical Systems, Graduate Studies in Mathematics, 140, AMS, Providence, Rhode Island, 2012.

X.Wang, G. Chen, A gallery of Lorenz-like and Chen-like attractors, International Journal of Bifurcation and Chaos, 23(2013), 1330011, 1–20.

C. L. Webber, N. Marwan (eds), Reccurence Quantification Analysis. Theory and Best Practice, Springer, NY, Dordrecht, Heidelberg, London, 2015.




DOI: http://dx.doi.org/10.15421/142109

Посилання

  • Поки немає зовнішніх посилань.



Індексування журналу

Журнал розміщено у наукометричних базах, репозитаріях та пошукових системах:

                 


Адреса редколегії: 49050, Україна, Дніпровський національний університет імені Олеся Гончара, вул. Козакова 18, корп. 14, механіко-математичний факультет, д-р фіз.-мат. наук, проф. Когут П.І. 

email: p.kogut@i.ua

www.dnu.dp.ua


Free counters! 

Лицензия Creative Commons
Це видання має доступ за ліцензією Creative Commons «Attribution» («Атрибуция») 4.0 Всемирная.


Open Science in Ukraine - website development