Neural Processing Letters

, Volume 49, Issue 1, pp 19–41 | Cite as

Neuro-Skins: Dynamics, Plasticity and Effect of Neuron Type and Cell Size on Their Response

  • Abdolreza Joghataie
  • Mehrdad Shafiei DizajiEmail author


We are introducing a new type of membrane, called neuro-skin or neuro-membrane. It is comprised of neurons embedded in a plastic membrane. The skin is smart and adaptive and is capable of providing desirable response to inputs intelligently. This way, the neuro-skin can be considered as a new type of neural network with adaptivity and learning capabilities. However, in this paper, only the response of neuro-skins to a dynamic input is studied. The membrane is modelled by nonlinear dynamic finite elements. Each finite element is considered as a cell of the neuro-skin which has a neuron. The neuron is the intelligent nucleus of the element. So, the finite elements are called finite neuro-elements (FNEs). Each FNE receives feedback excitation from its own neuron, as well as from its neighbouring neurons. Contrary to dynamic plastic continuous neural networks previously studied by the authors, the neurons in a neuro-skin do not apply concentrated loads but they apply traction stresses to the surface of NFEs. The membrane is in fact a skin made up of intelligent cells representing both neural activity and mechanical plasticity. The effect of neuron type and cell size on the response of neuro-skins is studied. Trainability is another issue which is not discussed in this paper. We have used the terms neuro-skin and neuro-membrane interchangeably.


Dynamic plastic continuous neural networks Neuro-skin Neuro-finite elements Plasticity 



The authors would like to thank the deputies of higher education and research of Sharif University of Technology for providing partial support during the course of this research.


  1. 1.
    Joghataie A, Torghabehi OO (2014) Simulating dynamic plastic continious neural networks by finite elements. IEEE Trans Neural Netw Learn Syst 25(8):1583–1587CrossRefGoogle Scholar
  2. 2.
    Amari SI (1990) Mathematical foundations of neurocomputing. Proc IEEE 78:1443–1463CrossRefGoogle Scholar
  3. 3.
    Arora JS (2004) Introduction to optimum design, 2nd edn. Elsevier Academic Press, San DiegoGoogle Scholar
  4. 4.
    Cohen MA, Grossberg S (1983) Absolute stability of global pattern formation and parallel memory storage by competitive neural networks. IEEE Trans Syst Man Cybern 13(5):815MathSciNetCrossRefzbMATHGoogle Scholar
  5. 5.
    Hopfield JJ (1984) Neurons with graded response have collective computational properties like those of two state neurons. Proc Nat Acad Sci 81:3088–3092CrossRefzbMATHGoogle Scholar
  6. 6.
    Hornik K, Stinhcombe M, White H (1989) Multilayer feed forward networks are universal approximators. Neural Netw 2:359–366CrossRefzbMATHGoogle Scholar
  7. 7.
    Guez A, Protopopsecu V, Barhen J (1988) On the stability, storage capacity, and design of nonlinear continuous neural networks. IEEE Trans Syst Man Cybern 18(1):80–87CrossRefGoogle Scholar
  8. 8.
    Chen ZY, Xu ZB (1994) Stability analysis on a class of nonlinear continuous neural networks. In: Proceedings of the IEEE international conference on computing intelligence, IEEE world congress computer intelligence, pp 1022–1027Google Scholar
  9. 9.
    Fromion V(2000) Lipschitz continuous neural networks on Lp. In: Proceedings of the 39th IEEE Conference on Decision Control, pp 3528–3533Google Scholar
  10. 10.
    Zurada JM, Kang MJ (1991) Numerical modeling of continuous-time fully coupled neural networks. In: Proceedings of the IEEE international joint conference on neural network, pp 1924–1929Google Scholar
  11. 11.
    Draye JPS, Pavisic DA, Cheron GA, Libert GA (1996) Dynamic recurrent neural networks: a dynamical analysis. IEEE Trans Syst Man Cybern B Cybern 26(5):692–706CrossRefGoogle Scholar
  12. 12.
    Sinha NK, Gupta MM, Rao DH (2000) Dynamic neural networks: an overview. In: Proceedings of the IEEE international conference on industrial technology, pp 491–496Google Scholar
  13. 13.
    Ruan J, Li L, Lin W (2001) Dynamics of some neural network models with delay. Phys Rev 63(5,):051906-1–051906-11Google Scholar
  14. 14.
    Takahashi YK, Kori H, Masuda N (2009) Self-organization of feed-forward structure and entrainment in excitatory neural networks with spike-timing-dependent plasticity. Phys Rev E 79:051904-1–051904-10MathSciNetCrossRefGoogle Scholar
  15. 15.
    Liao X, Xia Q, Qian Y, Zhang L, Hu G, Mi Y (2011) Pattern formation in oscillatory complex networks consisting of excitable nodes. Phys Rev 83:056204-1–056204-12Google Scholar
  16. 16.
    Gao Y, Wang J (2011) Oscillation propagation in neural networks with different topologies. Phys Rev 83:031909-1–031909-8MathSciNetGoogle Scholar
  17. 17.
    Xu G, Littlefair G, Penson R, Callan R (1999) Application of FE-based neural networks to dynamic problems. In: Proceedings of the 6th ICONIP, vol 3, pp 1039–1044Google Scholar
  18. 18.
    Ramuhalli P, Udpa L, Udpa SS (2005) Finite-element neural networks for solving differential equations. IEEE Trans Neural Netw 16(6):1381–1392CrossRefGoogle Scholar
  19. 19.
    Joghataie A, Farrokh MJ (2008) Dynamic analysis of nonlinear frames by Prandtl neural networks. J Eng Mech 134(11):961–969CrossRefGoogle Scholar
  20. 20.
    Chatzinakos, C, Tsouros C, Kofidis N, Margaris A (2008) A mutual information-based method for the estimation of the dimensions of chaotic dynamical systems using neural networks. In: Proceedings of the IAPR workshop cognitive information process, pp 148–152Google Scholar
  21. 21.
    Zhang H, Ye R, Cao J et al (2017) Delay-independent stability of Riemann-Liouville fractional neutral-type delayed neural networks. Neural Process Lett.
  22. 22.
    Zhang H, Ye R, Cao J, Alsaedi A (2017) Existence and globally asymptotic stability of equilibrium solution for fractional-order hybrid BAM neural networks with distributed delays and impulses. Complexity.
  23. 23.
    Ding X, Cao J, Alsaedi A, Alsaadi F, Hayat T (2017) Robust fixed-time synchronization for uncertain complex-valued neural networks with discontinuous activation functions. Neural Netw 90:42–55CrossRefGoogle Scholar
  24. 24.
    Cao J, Li R (2017) Fixed-time synchronization of delayed memristor-based recurrent neural networks. Sci China Inf Sci 60(3):032201MathSciNetCrossRefGoogle Scholar
  25. 25.
    Bao H, Park JH, Cao J (2016) Synchronization of fractional-order complex-valued neural networks with time delay. Neural Netw 81:16–28CrossRefzbMATHGoogle Scholar
  26. 26.
    Gong W, Liang J, Zhang C, Cao J (2016) Nonlinear measure approach for the stability analysis of complex-valued neural networks. Neural Process Lett 44(2):539–554CrossRefGoogle Scholar
  27. 27.
    Bao H, Park JH, Cao J (2016) Exponential synchronization of coupled stochastic memristor-based neural networks with time-varying probabilistic delay coupling and impulsive delay. IEEE Trans Neural Netw Learn Syst 27(1):190–201MathSciNetCrossRefGoogle Scholar
  28. 28.
    Bao H, Park JH, Cao J (2015) Adaptive synchronization of fractional-order memristor-based neural networks with time delay. Nonlinear Dyn 82(3):1343–1354MathSciNetCrossRefzbMATHGoogle Scholar
  29. 29.
    Song C, Cao J (2014) Dynamics in fractional-order neural networks. Neurocomputing 142:494–498CrossRefGoogle Scholar
  30. 30.
    Joghataie A, Dizaji MS (2016) Neuroplasticity in dynamic neural networks comprised of neurons attached to adaptive base plate. Neural Netwo 75:77–83CrossRefGoogle Scholar
  31. 31.
    Hornik K (1991) Approximation capabilities of multilayer feedforward networks. Neural Netw 4(2):251–257MathSciNetCrossRefGoogle Scholar
  32. 32.
    Bathe KJ (1996) Finite element procedure. Prentice-Hall, Upper Saddle RiverGoogle Scholar
  33. 33.
    Dunne F, Petrinic N (2006) Introduction to computational plasticity. Oxford University Press, New YorkzbMATHGoogle Scholar
  34. 34.
    Chopra AK (2001) Dynamics of structures-theory and application to earthquake engineering, 2nd edn. Prentice-Hall, Upper Saddle RiverGoogle Scholar
  35. 35.
    Farrokh M, Dizaji MS, Joghataie A (2015) Modeling hysteretic deteriorating behavior using generalized Prandtl neural network. ASCE J Eng Mech.
  36. 36.
    Joghataie A, Dizaji MS (2011) Transforming results from model to prototype of concrete gravity dams using neural networks. J Eng Mech.
  37. 37.
    Joghataie A, Dizaji MS (2013) Designing high precision fast nonlinear dam neuro-modellers and comparison with finite elements analysis. J Eng Mech.
  38. 38.
    Farrokh M, Dizaji MS (2015) Adaptive simulation of hysteresis using neuro-Madelung model. J Intell Mater Syst Struct.
  39. 39.
    Joghataie A, Dizaji MS (2009) Nonlinear analysis of concrete gravity dams by neural networks. In: Proceedings of the world congress on engineering. International Association of Engineers (IAENG), Newsood Limited, Hong Kong, pp 1022–1027Google Scholar
  40. 40.
    Brokate M, Sprekels J (1996) Hysteresis and phase transitions. Springer, New YorkCrossRefzbMATHGoogle Scholar

Copyright information

© Springer Science+Business Media, LLC, part of Springer Nature 2018

Authors and Affiliations

  1. 1.Structural engineering groupSharif University of TechnologyTehranIran
  2. 2.Structural Engineering GroupUniversity of VirginiaCharlottesvilleUSA

Personalised recommendations