Advertisement

Liquid State Machine by Spatially Coupled Oscillators

  • Andreas Herzog
  • Karsten Kube
  • Bernd Michaelis
  • Ana D. de Lima
  • Thomas Voigt
Part of the Lecture Notes in Computer Science book series (LNCS, volume 4221)

Abstract

Liquid State Machines [1] are a new strategie for real-time information processing in recurrent networks. In the present work we show that spatially coupled oscillators can be used as a usable liquid. If inputs stream are synchronized to oscillator phase its temporal dynamics can be be transformed into a high dimensional spatial pattern of oscillator activity. A memory less readout function can extract information about recent inputs. The fading memory is considered as the resynchronisation of oscillator field and can be adjusted by the parameter of small world connection mechanisms.

Keywords

Oscillator Phase Input Stream Synaptic Depression Fading Memory Recent Input 
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    Natschläger, T., Maass, W., Markram, H.: The liquid computer: A nover strategy for real-time computing on time series. Special Issue on Foundations of Information Processing of TELEMATIK, 32–36 (2002)Google Scholar
  2. 2.
    Maass, W., Markram, H.: On the computational power of recurrent circuits of spiking neurons. J. of Computer and System Sciences 69(4), 593–616 (2004)MATHCrossRefMathSciNetGoogle Scholar
  3. 3.
    Voigt, T., Opitz, T., de Lima, A.D.: Synchronous oscillatory activity in immature cortical network is driven by gabaergic preplate neurons. J. Neurosc. 21(22), 895–905 (2001)Google Scholar
  4. 4.
    Opitz, T., De Lima, A.D., Voigt, T.: Spontaneous development of synchronous oscillatory activity during maturation of cortical networks in vitro. J. Neurophys. 88, 2196–2206 (2002)CrossRefGoogle Scholar
  5. 5.
    Maeda, E., Robinson, H., Kawana, A.: The mechanisms of generation and propagation of synchronized bursting in developing networks of cortical neurons. J. Neurosc. 10(15), 6834–6845 (1995)Google Scholar
  6. 6.
    Watts, D., Strogatz, S.: Collective dynamics of ’small-world’ networks. Nature 393, 440–442 (1998)CrossRefGoogle Scholar
  7. 7.
    Kube, K., Herzog, A., Spravedlyvyy, V., Michaelis, B., Opitz, T., de Lima, A., Voigt, T.: Modelling of biologically plausible excitatory networks: Emergence and modulation of neural synchrony. In: ESANN 2004, pp. 379–384 (2004)Google Scholar
  8. 8.
    Tabak, J., Senn, W., O ’Donovan, M.J., Rinzel, J.: Modeling of spontaneous activity in developing spinal cord using activity-dependent depression in an excitatory network. J Neurosc, 3041–3056 (2000)Google Scholar
  9. 9.
    Herzog, A., Kube, K., Michaelis, B., de Lima, A.D., Voigt, T.: Simulation of young neocortical networks by sparcely couplet oscillators. In: IJCNN 2006 (in press, 2006)Google Scholar
  10. 10.
    Herzog, A., Kube, K., Michaelis, B., de Lima, A.D., Voigt, T.: Connection strategies in neocortical networks. In: Proceedings of the ESANN 2006 European Symposium on Artificial Neural Networks, pp. 215–220 (2006)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2006

Authors and Affiliations

  • Andreas Herzog
    • 1
  • Karsten Kube
    • 1
  • Bernd Michaelis
    • 1
  • Ana D. de Lima
    • 2
  • Thomas Voigt
    • 2
  1. 1.Institute of ElectronicsSignal Processing and Communications 
  2. 2.Institute of PhysiologyOtto-von-Guericke University MagdeburgMagdeburgGermany

Personalised recommendations