Advertisement

Cognitive Computation

, Volume 2, Issue 4, pp 265–271 | Cite as

A Simple Recurrent Network for Implicit Learning of Temporal Sequences

  • Stefan Glüge
  • Oussama H. Hamid
  • Andreas Wendemuth
Article

Abstract

A behavioural paradigm for learning arbitrary visuo-motor associations established that human observers learn to associate visual objects with their corresponding motor responses faster if the objects follow a temporal rule rather than if they were presented in a random order. Here, we use a simple recurrent network with a back propagation training algorithm adapted to a reinforcement learning scheme. Our simulations fit quantitatively as well as qualitatively to the behavioural results, endorsing the role of temporal context in associative learning scenarios.

Keywords

Elman network Sequence learning Reinforcement learning Visuo-motor associations Behavioural models 

Notes

Acknowledgments

The authors acknowledge the support provided by the federal state Sachsen-Anhalt with the Graduiertenförderung (LGFG scholarship).

References

  1. 1.
    Ackley DH, Littman ML. Generalization and scaling in reinforcement learning. In: Advances in neural information processing systems 2. Morgan Kaufmann; 1990. p. 550–7.Google Scholar
  2. 2.
    Cleeremans A. Mechanisms of implicit learning: connectionist models of sequence processing. Cambridge:MIT;1993.Google Scholar
  3. 3.
    Elman JL. Finding structure in time. Cogn Sci. 1990;14:179–211.CrossRefGoogle Scholar
  4. 4.
    Grüning A (2007) Elman backpropagation as reinforcement for simple recurrent networks. Neural Comput. 2007;19(11):3108–31.CrossRefPubMedGoogle Scholar
  5. 5.
    Hamid O, Wendemuth A, Braun J. Temporal context and conditional associative learning. BMC Neurosci. 2010;11(1):45. doi: 10.1186/1471-2202-11-45. URL:http://www.biomedcentral.com/1471-2202/11/45.
  6. 6.
    Mandler G, Dean PJ. Seriation: development of serial order in free recall. J Exp Psychol. 1969;81(2):207–15.CrossRefGoogle Scholar
  7. 7.
    Mazzoni P, Andersen RA, Jordan MI. A more biologically plausible learning rule for neural networks. Proc Natl Acad Sci USA. 1991;88(10):4433–7CrossRefPubMedGoogle Scholar
  8. 8.
    Miyashita Y, Chang HS. Neuronal correlate of pictorial short-term memory in the primate temporal cortex. Nature. 1988; 331:68–70.CrossRefPubMedGoogle Scholar
  9. 9.
    Reber AS. Implicit learning of artificial grammars. J Verbal Learn Verbal Behav. 1967;6(6):855–63.CrossRefGoogle Scholar
  10. 10.
    Reber AS. Implicit learning and tacit knowledge. J Exp Psychol Gen. 1989;118(3):219–35.CrossRefGoogle Scholar
  11. 11.
    Sutton RS, Barto AG. Reinforcement learning: an introduction. Adapt Comput Mach Learn. 1998;Mit Pr.Google Scholar
  12. 12.
    Werfel J, Xie X, Seung HS. Learning curves for stochastic gradient descent in linear feedforward networks. Neural Comput. 2005;17(12):2699–718.CrossRefPubMedGoogle Scholar
  13. 13.
    Yakovlev V, Fusi S, Berman E, Zohary E. Inter-trial neuronal activity in inferior temporal cortex: a putative vehicle to generate long-term visual associations. Nat Neurosci.1998;1:310–7.CrossRefPubMedGoogle Scholar

Copyright information

© Springer Science+Business Media, LLC 2010

Authors and Affiliations

  • Stefan Glüge
    • 1
  • Oussama H. Hamid
    • 2
  • Andreas Wendemuth
    • 1
  1. 1.Faculty of Electrical Engineering and Information TechnologyOtto von Guericke University MagdeburgMagdeburgGermany
  2. 2.Cognitive Biology, Institute of Biology (Bldg. 91)Otto von Guericke University MagdeburgMagdeburgGermany

Personalised recommendations