Advertisement

Infinite Order Systems of Differential Equations and Large Scale Random Neural Networks

  • Soltan K. Kanzitdinov
  • Sergey A. VasilyevEmail author
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 10684)

Abstract

In this paper we consider dynamics of complex systems using random neural networks with an infinite number of cells. The Cauchy problem for singular perturbed infinite order systems of stochastic differential equations which describes the random neural network with infinite number of cells is studied.

Keywords

Analytical methods in probability theory Systems of differential equations of infinite order Singular perturbated systems of differential equations Small parameter Neural network Dynamics of complex systems 

Notes

Acknowledgment

The publication was prepared with the support of the “RUDN University Program 5-100” and partially funded by RFBF grants No. 15-07-08795, No. 16-07-00556.

References

  1. 1.
    Calvert, B.D.: Neural networks with an infinite number of cells. J. Differ. Equ. 186(1), 31–51 (2002)MathSciNetCrossRefGoogle Scholar
  2. 2.
    Calvert, B.D., Zemanian, A.H.: Operating points in infinite nonlinear networks approximated by finite networks. Trans. Am. Math. Soc. 352(2), 753–780 (2000)MathSciNetCrossRefzbMATHGoogle Scholar
  3. 3.
    Daletsky, Y.L., Krein, M.G.: Stability of Solutions of Differential Equations in Banach Space. Science Publisher, Moscow (1970)Google Scholar
  4. 4.
    Gaidamaka, Y., Sopin, E., Talanova, M.: Approach to the analysis of probability measures of cloud computing systems with dynamic scaling. In: Vishnevsky, V., Kozyrev, D. (eds.) DCCN 2015. CCIS, vol. 601, pp. 121–131. Springer, Cham (2016).  https://doi.org/10.1007/978-3-319-30843-2_13 CrossRefGoogle Scholar
  5. 5.
    Hopfield, J.J.: Neurons with graded response have collective computational properties like those of two state neurons. Proc. Natl. Acad. Sci. USA 81, 3088–3092 (1984)CrossRefzbMATHGoogle Scholar
  6. 6.
    Huang, H., Du, O., Kang, X.: Global exponential stability of neutral high-order stochastic Hopfield neural networks with Markovian jump parameters and mixed time delays. ISA Trans. 52(6), 759–767 (2013)CrossRefGoogle Scholar
  7. 7.
    Korobeinik, J.: Differential equations of infinite order and infinite systems of differential equations. Izv. Akad. Nauk SSSR Ser. Mat. 34, 881–922 (1970)MathSciNetGoogle Scholar
  8. 8.
    Korolkova, A.V., Eferina, E.G., Laneev, E.B., Gudkova, I.A., Sevastianov, L.A., Kulyabov, D.S.: Stochastization of one-step processes in the occupations number representation. In: Proceedings - 30th European Conference on Modelling and Simulation, ECMS 2016, pp. 698–704 (2016)Google Scholar
  9. 9.
    Krasnoselsky, M.A., Zabreyko, P.P.: Geometrical Methods of Nonlinear Analysis. Springer, Berlin (1984)CrossRefGoogle Scholar
  10. 10.
    Lomov, S.A.: The construction of asymptotic solutions of certain problems with parameters. Izv. Akad. Nauk SSSR Ser. Mat. 32, 884–913 (1968)MathSciNetGoogle Scholar
  11. 11.
    Cho, M.W.: Competitive learning behavior in a stochastic neural network. J. Korean Phys. Soc. 67(9), 1679–1685 (2015)CrossRefGoogle Scholar
  12. 12.
    Persidsky, K.P.: Izv. AN KazSSR, Ser. Mat. Mach. 2, 3–34 (1948)Google Scholar
  13. 13.
    Samoilenko, A.M., Teplinskii, Y.V.: Countable Systems of Differential Equations. Brill, Leiden (2003)CrossRefzbMATHGoogle Scholar
  14. 14.
    Samouylov, K., Naumov, V., Sopin, E., Gudkova, I., Shorgin, S.: Sojourn time analysis for processor sharing loss system with unreliable server. In: Wittevrongel, S., Phung-Duc, T. (eds.) ASMTA 2016. LNCS, vol. 9845, pp. 284–297. Springer, Cham (2016).  https://doi.org/10.1007/978-3-319-43904-4_20 CrossRefGoogle Scholar
  15. 15.
    Turchetti, C.: Stochastic Models of Neural Networks. Frontiers in Artificial Intelligence and Applications Knowledge-Based Intelligent Engineering Systems, vol. 102. IOS Press, Amsterdam (2004)zbMATHGoogle Scholar
  16. 16.
    Turchetti, C., Crippa, P., Pirani, M., Biagetti, G.: Representation of nonlinear random transformations by non-Gaussian stochastic neural networks. IEEE Trans. Neural Netw. 19, 1033–1060 (2008). A Publication of the IEEE Neural Networks CouncilCrossRefGoogle Scholar
  17. 17.
    Tihonov, A.N.: Uber unendliche Systeme von Differentialgleichungen. Rec. Math. 41(4), 551–555 (1934)Google Scholar
  18. 18.
    Tihonov, A.N.: Systems of differential equations containing small parameters in the derivatives. Matematicheskii Sbornik (N.S.) 31(73), 575–586 (1952)MathSciNetGoogle Scholar
  19. 19.
    Vasilyev, S.A., Kanzitdinov, S.K.: Model of neural networks with an infinite number of cells and small parameter. Int. Sci. J. Modern Inf. Technol. IT-Educ. 12(2), 15–20 (2016)Google Scholar
  20. 20.
    Vasil’eva, A.B.: Asymptotic behaviour of solutions of certain problems for ordinary non-linear differential equations with a small parameter multiplying the highest derivatives. Uspehi Mat. Nauk. 18(111(3)), 15–86 (1963)MathSciNetGoogle Scholar
  21. 21.
    Zhautykov, O.A.: On a countable system of differential equations with variable parameters. Matematicheskii Sbornik (N.S.) 49(91), 317–330 (1959)MathSciNetGoogle Scholar
  22. 22.
    Zhautykov, O.A.: Extension of the Hamilton-Jacobi theorems to an infinite canonical system of equations. Matematicheskii Sbornik (N.S.) 53(95), 313–328 (1961)MathSciNetzbMATHGoogle Scholar
  23. 23.
    Liang, X., Wang, L., Wang, Y., Wang, R.: Dynamical behavior of delayed reaction-diffusion Hopfield neural networks driven by infinite dimensional Wiener processes. IEEE Trans. Neural Netw. 27(9), 1816–1826 (2016)MathSciNetCrossRefGoogle Scholar

Copyright information

© Springer International Publishing AG 2017

Authors and Affiliations

  1. 1.Department of Applied Probability and InformaticsRUDN UniversityMoscowRussia

Personalised recommendations