Advertisement

Information Theoretic Self-organised Adaptation in Reservoirs for Temporal Memory Tasks

  • Sakyasingha Dasgupta
  • Florentin Wörgötter
  • Poramate Manoonpong
Part of the Communications in Computer and Information Science book series (CCIS, volume 311)

Abstract

Recurrent neural networks of the Reservoir Computing (RC) type have been found useful in various time-series processing tasks with inherent non-linearity and requirements of temporal memory. Here with the aim to obtain extended temporal memory in generic delayed response tasks, we combine a generalised intrinsic plasticity mechanism with an information storage based neuron leak adaptation rule in a self-organised manner. This results in adaptation of neuron local memory in terms of leakage along with inherent homeostatic stability. Experimental results on two benchmark tasks confirm the extended performance of this system as compared to a static RC and RC with only intrinsic plasticity. Furthermore, we demonstrate the ability of the system to solve long temporal memory tasks via a simulated T-shaped maze navigation scenario.

Keywords

Recurrent neural networks Self-adaptation Information theory Intrinsic plasticity 

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    Schrauwen, B., Wardermann, M., Verstraeten, D., Steil, J.J., Stroobandt, D.: Improving Reservoirs using Intrinsic Plasticity. Neurocomputing 71, 1159–1171 (2008)CrossRefGoogle Scholar
  2. 2.
    Jaeger, H., Lukosevicius, M., Popovici, D., Siewert, U.: Optimization and Applications of Echo State Networks with Leaky-integrator Neurons. Neural Networks 20, 335–352 (2007)MATHCrossRefGoogle Scholar
  3. 3.
    Lukoševičius, M., Jaeger, H.: Reservoir Computing Approaches to Recurrent Neural Network Training. Computer Science Review 3, 127–149 (2009)CrossRefGoogle Scholar
  4. 4.
    Li, C.: A model of Neuronal Intrinsic Plasticity. IEEE Trans. on Autonomous Mental Development 3, 277–284 (2011)CrossRefGoogle Scholar
  5. 5.
    Antonelo, E., Schrauwen, B., Stroobandt, D.: Mobile Robot Control in the Road Sign Problem using Reservoir Computing Networks. In: Proceedings of the IEEE Int. Conf. on Robotics and Automation, ICRA (2008)Google Scholar
  6. 6.
    Triesch, J.: Synergies between Intrinsic and Synaptic Plasticity Mechanisms. Neural Computation 4, 885–909 (2007)MathSciNetCrossRefGoogle Scholar
  7. 7.
    Lizier, T.J., Pritam, M., Prokopenko, M.: Information Dynamics in Small-world Boolean Networks. Artificial Life 17, 293–314 (2011)CrossRefGoogle Scholar
  8. 8.
    Boedecker, J., Obst, O., Mayer, M.N., Asada, M.: Initialization and Self-Organized Optimization of Recurrent Neural Network Connectivity. HFSP Journal 5, 340–349 (2009)CrossRefGoogle Scholar
  9. 9.
    Ganguli, S., Dongsung, H., Sompolinsky, H.: Memory Traces in Dynamical Systems. PNAS 105, 18970–18975 (2008)CrossRefGoogle Scholar
  10. 10.
    Steingrube, S., Timme, M., Wörgötter, F., Manoonpong, P.: Self-Organized Adaptation of a Simple Neural Circuit Enables Complex Robot Behaviour. Nature Physics 6, 224–230 (2010)CrossRefGoogle Scholar
  11. 11.
    Jaeger, H.: Adaptive Nonlinear System Identification with Echo State Networks. In: Advances in Neural Information Processing Systems, vol. 15 (2003)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2012

Authors and Affiliations

  • Sakyasingha Dasgupta
    • 1
  • Florentin Wörgötter
    • 1
  • Poramate Manoonpong
    • 1
  1. 1.Bernstein Center for Computational NeuroscienceGeorg-August-UniversitätGöttingenGermany

Personalised recommendations