Constructing Robust Liquid State Machines to Process Highly Variable Data Streams

  • Stefan Schliebs
  • Maurizio Fiasché
  • Nikola Kasabov
Part of the Lecture Notes in Computer Science book series (LNCS, volume 7552)

Abstract

In this paper, we propose a mechanism to effectively control the overall neural activity in the reservoir of a Liquid State Machine (LSM) in order to achieve both a high sensitivity of the reservoir to weak stimuli as well as an improved resistance to over-stimulation for strong inputs. The idea is to employ a mechanism that dynamically changes the firing threshold of a neuron in dependence of its spike activity. We experimentally demonstrate that reservoirs employing this neural model significantly increase their separation capabilities. We also investigate the role of dynamic and static synapses in this context. The obtained results may be very valuable for LSM based real-world application in which the input signal is often highly variable causing problems of either too little or too much network activity.

Keywords

Liquid State Machine Spiking Neural Networks Reservoir Computing 

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    Apolloni, B., Bassis, S., Clivio, A., Gaito, S., Malchiodi, D.: Modeling individuals aging within a bacterial population using a pi-calculus paradigm. Natural Computing 6, 33–53 (2007)MathSciNetMATHCrossRefGoogle Scholar
  2. 2.
    Gerstner, W., Kistler, W.M.: Spiking Neuron Models: Single Neurons, Populations, Plasticity. Cambridge University Press, Cambridge (2002)MATHCrossRefGoogle Scholar
  3. 3.
    Goodman, D., Brette, R.: Brian: A simulator for spiking neural networks in Python. BMC Neuroscience 9(suppl. 1), P92 (2008)CrossRefGoogle Scholar
  4. 4.
    Goodman, E., Ventura, D.: Spatiotemporal pattern recognition via liquid state machines. In: International Joint Conference on Neural Networks, Vancouver, BC, pp. 3848–3853 (2006)Google Scholar
  5. 5.
    Kasinski, A.J., Ponulak, F.: Comparison of supervised learning methods for spike time coding in spiking neural networks. Int. J. of Applied Mathematics and Computer Science 16, 101–113 (2006)MathSciNetGoogle Scholar
  6. 6.
    Lukoševičius, M., Jaeger, H.: Reservoir computing approaches to recurrent neural network training. Computer Science Review 3(3), 127–149 (2009)CrossRefGoogle Scholar
  7. 7.
    Maass, W., Natschläger, T., Markram, H.: Real-time computing without stable states: A new framework for neural computation based on perturbations. Neural Computation 14(11), 2531–2560 (2002)MATHCrossRefGoogle Scholar
  8. 8.
    Markram, H., Wang, Y., Tsodyks, M.: Differential signaling via the same axon of neocortical pyramidal neurons. Proceedings of the National Academy of Sciences 95(9), 5323–5328 (1998)CrossRefGoogle Scholar
  9. 9.
    Norton, D., Ventura, D.: Preparing more effective liquid state machines using Hebbian learning. In: International Joint Conference on Neural Networks, IJCNN 2006, pp. 4243–4248. IEEE, Vancouver (2006)CrossRefGoogle Scholar
  10. 10.
    Norton, D., Ventura, D.: Improving liquid state machines through iterative refinement of the reservoir. Neurocomputing 73(16-18), 2893–2904 (2010)CrossRefGoogle Scholar
  11. 11.
    Schrauwen, B., Verstraeten, D., Campenhout, J.V.: An overview of reservoir computing: theory, applications and implementations. In: Proceedings of the 15th European Symposium on Artificial Neural Networks, pp. 471–482 (2007)Google Scholar
  12. 12.
    Verstraeten, D., Schrauwen, B., D’Haene, M., Stroobandt, D.: An experimental unification of reservoir computing methods. Neural Networks 20(3), 391–403 (2007)MATHCrossRefGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2012

Authors and Affiliations

  • Stefan Schliebs
    • 1
  • Maurizio Fiasché
    • 2
  • Nikola Kasabov
    • 1
  1. 1.Knowledge Engineering and Discovery Research InstituteAuckland University of TechnologyNew Zealand
  2. 2.Department of Mathematics ”F. Brioschi”Polytechnic Institute of MilanMilanItaly

Personalised recommendations