Advertisement

Spike-Timing Dependent Plasticity Learning for Visual-Based Obstacles Avoidance

  • Hédi Soula
  • Guillaume Beslon
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 4095)

Abstract

In this paper, we train a robot to learn online a task of obstacles avoidance. The robot has at its disposal only its visual input from a linear camera in an arena whose walls are composed of random black and white stripes. The robot is controlled by a recurrent spiking neural network (integrate and fire). The learning rule is the spike-time dependent plasticity (STDP) and its counterpart – the so-called anti-STDP. Since the task itself requires some temporal integration, the neural substrate is the network’s own dynamics. The behaviors of avoidance we obtain are homogenous and elegant. In addition, we observe the emergence of a neural selectivity to the distance after the learning process.

Keywords

Hide Neuron Learning Rule Spike Activity Obstacle Avoidance Neural Computation 
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.
    Harvey, I., Di Paolo, E., Wood, R., Quinn, M.: Evolutionary robotics: A new scientific tool for studying cognition. Artificial Life 11(1-2), 79–98 (2005)CrossRefGoogle Scholar
  2. 2.
    Soula, H., Beslon, G., Favrel, J.: Evolving spiking neurons nets to control an animat. In: Pearson, D., Steel, N., Albrecht, R. (eds.) Proc. of ICANN-GA, Roanne, France, pp. 193–197 (2003)Google Scholar
  3. 3.
    di Paolo, E.: Evolving spike-timing-dependent plasticity for single-trial learning in robots. Phil. Trans. R. Soc. Lond. A. 361, 2299–2319 (2003)CrossRefGoogle Scholar
  4. 4.
    Floreano, D., Mattiusi, C.: Evolution of spiking neural controllers for autonomous vision-based robots. In: Gomi, T. (ed.) Evolutionnary Robotics. Springer, Heidelberg (2001)Google Scholar
  5. 5.
    Tuckwell, H.C.: Introduction to theoretical neurobiology: Non linear and stochastic theories, vol. 2. Cambridge University Press, Cambridge (1988)Google Scholar
  6. 6.
    van Vreeswijk, C., Sompolinsky, H.: Chaos in neuronal networks with balanced excitatory and inhibitory activity. Science 274, 1724–1726 (1996)CrossRefGoogle Scholar
  7. 7.
    Nykamp, D.Q., Tranchina, D.: A population density approach that facilitates large-scale modeling of neural networks: Analysis and an application to orientation tuning. Journal of Computational Neuroscience 8, 19–50 (2000)MATHCrossRefGoogle Scholar
  8. 8.
    Meyer, C., van Vreeswijk, C.: Temporal correlations in stochastic networks of spiking neurons. Neural Computation 14(2), 369–404 (2002)MATHCrossRefGoogle Scholar
  9. 9.
    Chow, C.C.: Phase-locking in weakly heterogeneous neural networks. Physica D. 118, 343–370 (1998)MATHCrossRefMathSciNetGoogle Scholar
  10. 10.
    Gerstner, W.: Population dynamics of spiking neurons: fast transients, asynchronous states and locking. Neural Computation 12, 43–89 (2000)CrossRefGoogle Scholar
  11. 11.
    Brunel, N.: Dynamics of sparsely connected networks of excitatory and inhibitory spiking neurons. Journal of Computational Neuroscience 8, 183–208 (2000)MATHCrossRefGoogle Scholar
  12. 12.
    Amit, D.J., Brunel, N.: Model of global spontaneous activity and local structured delay activity during learning periods in the cerebral cortex. Cerebral Cortex 7, 237–252 (1997)CrossRefGoogle Scholar
  13. 13.
    Fusi, S., Mattia, M.: Collective behavior of networks with linear (vlsi) integrate-and-fire neurons. Neural Computation 11, 633–652 (1999)CrossRefGoogle Scholar
  14. 14.
    Mattia, M., del Giudice, P.: Population dynamics of interacting spiking neurons. Physical Review E 66(5) (2002)Google Scholar
  15. 15.
    Soula, H., Beslon, G., Mazet, O.: Spontaneous dynamics of assymmetric random recurrent spiking neural networks. Neural Computation 18(1) (2006)Google Scholar
  16. 16.
    Bi, G., Poo, M.: Synaptic modifications in cultured hippocampal neurons: Dependence on spike timing, synaptic strength, and postsynaptic cell type. The Journal of Neuroscience 18(24), 10464–10472 (1998)Google Scholar
  17. 17.
    Abbott, L.F., Nelson, S.B.: Synaptic plasticity: taming the beast. Nature America 3, 1178–1182 (2000)Google Scholar
  18. 18.
    Hebb, D.O.: The Organization of Behavior. Wiley, Chichester (1949)Google Scholar
  19. 19.
    Rao, R.P.N., Sejnowski, T.J.: Spike-timing-dependent hebbian plasticity as temporal difference learning. Neural Computation 13, 2221–2237 (2001)MATHCrossRefGoogle Scholar
  20. 20.
    Song, S., Miller, K.D., Abbott, L.F.: Competitive hebbian learning through spike-timing dependent plasticity. Nature Neuroscience 3, 919–926 (2000)CrossRefGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2006

Authors and Affiliations

  • Hédi Soula
    • 1
  • Guillaume Beslon
    • 2
  1. 1.LBM/NIDDKNational Institutes of HealthBethesdaUSA
  2. 2.PRISMANational Institute of Applied SciencesVilleurbanne CedexFrance

Personalised recommendations