Synchrony based learning rule of Hopfield like chaotic neural networks with desirable structure

Cognitive Neurodynamics volume 8, pages 151–156 (2014)Cite this article

Abstract

In this paper a new learning rule for the coupling weights tuning of Hopfield like chaotic neural networks is developed in such a way that all neurons behave in a synchronous manner, while the desirable structure of the network is preserved during the learning process. The proposed learning rule is based on sufficient synchronization criteria, on the eigenvalues of the weight matrix belonging to the neural network and the idea of Structured Inverse Eigenvalue Problem. Our developed learning rule not only synchronizes all neuron’s outputs with each other in a desirable topology, but also enables us to enhance the synchronizability of the networks by choosing the appropriate set of weight matrix eigenvalues. Specifically, this method is evaluated by performing simulations on the scale-free topology.

This is a preview of subscription content, access via your institution.

Access options

Buy single article

Instant access to the full article PDF.

43,34 €

Tax calculation will be finalised during checkout.

Fig. 1
Fig. 2
Fig. 3

References

  1. Aihara K, Takada T, Toyoda M (1990) Chaotic neural networks. Phys Lett A 144:333–340

    Article  Google Scholar 

  2. Anninos P, Beek B, Harth E, Pertile G (1970) Dynamics of neural structures. J Theor Biol 26:121–148

    CAS  PubMed  Article  Google Scholar 

  3. Babloyantz A, Lourenco C (1994) Computation with chaos: a paradigm for cortical activity. Proc Natl Acad Sci USA 91:9027–9031

    CAS  PubMed Central  PubMed  Article  Google Scholar 

  4. Barabasi AL, Albert R (1999) Emergence of scaling in random networks. Science 286:509–512

    PubMed  Article  Google Scholar 

  5. Churchland PS, Sejnowski TJ (1989) The computational brain. MIT press, Cambridge

    Google Scholar 

  6. Comellas F, Gago S (2007) Synchronizability of complex networks. J of Phys A: Math and Theor 40:4483–4492

    Article  Google Scholar 

  7. Farhat NH (1998) Biomorphic dynamical networks for cognition and control. J Intell Robot Syst 21:167–177

    Article  Google Scholar 

  8. Farhat NH (2000) Corticonics: the way to designing machines with brain like intelligence. Proc SPIE Critical Technol Future Comput 4109:103–109

    Article  Google Scholar 

  9. Harth E (1983) Order and chaos in neural systems: an approach to the dynamics of higher brain functions. IEEE Trans Syst Man Cybern 13:782–789

    Article  Google Scholar 

  10. Harth E, Csermely TJ, Beek B, Lindsay RD (1970) Brain function and neural dynamics. J Theor Biol 26:93–120

    CAS  PubMed  Article  Google Scholar 

  11. Izhikevich EM (2007) Dynamical systems in neuroscience. MIT Press, Cambridge

    Google Scholar 

  12. Lee RST (2004) A transient-chaotic auto associative network based on Lee oscilator. IEEE Trans on Neural Networks 15:1228–1243

    CAS  Article  Google Scholar 

  13. Lee G, Farhat NH (2001) Parametrically coupled sine map networks. Int J Bifurcat Chaos 11:1815–1834

    Article  Google Scholar 

  14. Li Z, Chen G (2006) Global synchronization and asymptotic stability of complex dynamical networks. IEEE Trans on Circuits and Systems-II 53:28–33

    Article  Google Scholar 

  15. Li Z, Jiao L, Lee J (2008) Robust adaptive global synchronization of complex dynamical networks by adjusting time-varying coupling strength. PhysicaA 387:1369–1380

    Article  Google Scholar 

  16. Liu H, Chen J, Lu J, Cao M (2010) Generalized synchronization in complex dynamical networks via adaptive couplings. PhysicaA 389:1759–1770

    CAS  Article  Google Scholar 

  17. Lopez-Ruiz R, Fournier-Prunaret D (2009) Periodic and chaotic events in a discrete model of logistic type for the competitive interaction of two species. Chaos, Solitons Fractals 41:334–347

    Article  Google Scholar 

  18. Lü J, Yu X, Chen G (2004) Chaos synchronization of general complex dynamical networks. PhysicaA 334:281–302

    Article  Google Scholar 

  19. Ma J, Wu J (2006) Bifurcation and multistability in coupled neural networks with non-monotonic communication. Technical report Math dept, York University, Toronto

    Google Scholar 

  20. Mahdavi N, Menhaj MB (2011) A new set of sufficient conditions based on coupling parameters for synchronization of Hopfield like chaotic neural networks. Int J control Auto and Syst 9:104–111

    Article  Google Scholar 

  21. Moody TC, Golub GH (2005) Inverse eigenvalue problems: theory, algorithms and applications. Numerical mathematics and scientific computation series. Oxford press, Oxford

    Google Scholar 

  22. Mpitsos GJ, Burton RM, Creech HC, Soinila SO (1988a) Evidence for chaos in spike trains of neurons that generate rhythmic motor patterns. Brain Res Bull 21:529–538

    CAS  PubMed  Article  Google Scholar 

  23. Mpitsos GJ, Burton RM, Creech HC (1988b) Connectionist networks learn to transmit chaos. Brain Res Bull 21:539–546

    CAS  PubMed  Article  Google Scholar 

  24. Nakano H, Saito T (2004) Grouping synchronization in a pulse-coupled network of chaotic spiking oscillators. IEEE Trans Neural Networks 15:1018–1026

    CAS  Article  Google Scholar 

  25. Pashaie R, Farhat NH (2009) Self organization in a parametrically coupled logistic map network: a model for information processing in the Visual Cortex. IEEE Trans on Neural Networks 20:597–608

    Article  Google Scholar 

  26. Ponce MC, Masoller C, Marti AC (2009) Synchronizability of chaotic logistic maps in delayed complex networks. Eur Phys J B 67:83–93

    Article  Google Scholar 

  27. Singer W (1999) Neuronal synchrony: a versatile code for the definition of relations? Neuron 24:49–65

    CAS  PubMed  Article  Google Scholar 

  28. Tanaka G, Aihara K (2005) Multistate associative memory with parametrically coupled map networks. Int J Bifurcat Chaos 15:1395–1410

    Article  Google Scholar 

  29. Uhlhaas PJ, Singer W (2006) Neural synchrony in brain disorders: relevance for cognitive dysfunctions and pathophysiology. Neuron 52:155–168

    CAS  PubMed  Article  Google Scholar 

  30. Wang L (2007) Interactions between neural networks: a mechanism for tuning chaos and oscillations. Cogn Neurodyn 1:185–188

    PubMed Central  PubMed  Article  Google Scholar 

  31. Wang L, Ross J (1990) Interactions of neural networks: model for distraction and concentration. Proc Natl Acad Sci USA 87:7110–7114

    CAS  PubMed Central  PubMed  Article  Google Scholar 

  32. Wang L, Pichler EE, Ross J (1990) Oscillations and chaos in neural networks: an exactly solvable model. Proc Natl Acad Sci USA 87:9467–9471

    CAS  PubMed Central  PubMed  Article  Google Scholar 

  33. Wang L, Yu W, Shi H, Zurada JM (2007) Cellular neural networks with transient chaos. IEEE Trans on circuits and systems-II: express briefs 54:440–444

    Article  Google Scholar 

  34. Wang WX, Huang L, Lai YC, Chen G (2009) Onset of synchronization in weighted scale-free networks. Chaos 19:013134

    PubMed  Article  Google Scholar 

  35. Watts DJ, Strogatz SH (1998) Collective dynamics of small-world networks. Nature 393:440–442

    CAS  PubMed  Article  Google Scholar 

  36. Xu YH, Zhou WN, Fang JA, Lu HQ (2009) Structure identification and adaptive synchronization of uncertain general complex dynamical networks. Phys Lett A 374:272–278

    CAS  Article  Google Scholar 

  37. Zhou C, Kurths J (2006) Dynamical weights and enhanced synchronization in adaptive complex networks. Phys Rev Lett 96:164102

    PubMed  Article  Google Scholar 

Download references

Author information

Affiliations

  1. Potsdam Institute for Climate Impact Research, Potsdam, Germany

    Nariman Mahdavi & Jürgen Kurths

Authors
  1. Nariman Mahdavi
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Jürgen Kurths
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Nariman Mahdavi.

Rights and permissions

Reprints and Permissions

About this article

Cite this article

Mahdavi, N., Kurths, J. Synchrony based learning rule of Hopfield like chaotic neural networks with desirable structure. Cogn Neurodyn 8, 151–156 (2014). https://doi.org/10.1007/s11571-013-9260-2

Download citation

Keywords

  • Synchrony based learning
  • Chaotic neural networks
  • Structure inverse eigenvalue problem
  • Scale-free networks