IMPLICIT SEQUENCE LEARNING - A Case Study with a 4–2–4 Encoder Simple Recurrent Network

Stefan Glüge, Ronald Böck, Andreas Wendemuth

2010

Abstract

Without any doubt the temporal order inherent in a task is an important issue during human learning. Recurrent neural networks are known to be a useful tool to model implicit sequence learning. In terms of the psychology of learning, recurrent networks might be suitable to build a model to reproduce the data obtained from experiments with human subjects. Such model should not just reproduce the data but also explain it and further make verifiable predictions. Therefore, one basic requirement is an understanding of the processes in the network during learning. In this paper, we investigate how (implicitly learned) temporal information is stored/represented in a simple recurrent network. To be able to study detailed effects we use a small network and a standard encoding task for this study.

References

  1. Cleeremans, A. (1993). Mechanisms of implicit learning: connectionist models of sequence processing. MIT Press, Cambridge, MA, USA.
  2. Conway, J. (1990). A Course in Functional Analysis (Graduate texts in mathematics). Springer.
  3. Elman, J. L. (1990). Finding structure in time. Cognitive Science, 14:179-211.
  4. Glüge, S., Hamid, O., and Wendemuth, A. (2010). Influence of the temporal context on a simple recurrent network in a classification task. In 7th International Symposium on Neural Networks (ISNN 2010).
  5. Gupta, L. and McAvoy, M. (2000). Investigating the prediction capabilities of the simple recurrent neural network on real temporal sequences. Pattern Recognition, 33(12):2075 - 2081.
  6. Hamid, O., Wendemuth, A., and Braun, J. (2010). Temporal context and conditional associative learning. BMC Neuroscience, 11(1):45.
  7. Heskes, T. M. and Kappen, B. (1991). Learning processes in neural networks. Phys. Rev. A, 44(4):2718-2726.
  8. Heskes, T. M. and Kappen, B. (1993). Mathematical approaches to neural networks, chapter On-line learning processes in artificial neural networks, pages 199- 233. Elsevier Science Publishers B. V.
  9. Mandler, G. and Dean, P. J. (1969). Seriation: Development of serial order in free recall. Journal of Experimental Psychology, 81(2):207-215.
  10. Reber, A. S. (1989). Implicit learning and tacit knowledge. Journal of Experimental Psychology: General, 118(3):219-235.
  11. Slus?nÉ, S., Vidnerová, P., and Neruda, R. (2007). Behavior emergence in autonomous robot control by means of feedforward and recurrent neural networks. Proceedings of the World Congress on Engineering and Computer Science 2007 WCECS 2007, October 24- 26, 2007, San Francisco, USA.
  12. Ü beyli, E. D. and Übeyli, M. (2008). Recurrent Neural Networks, chapter Case Studies for Applications of Elman Recurrent Neural Networks. InTech, Croatia.
Download


Paper Citation


in Harvard Style

Glüge S., Böck R. and Wendemuth A. (2010). IMPLICIT SEQUENCE LEARNING - A Case Study with a 4–2–4 Encoder Simple Recurrent Network . In Proceedings of the International Conference on Fuzzy Computation and 2nd International Conference on Neural Computation - Volume 1: ICNC, (IJCCI 2010) ISBN 978-989-8425-32-4, pages 279-288. DOI: 10.5220/0003061402790288


in Bibtex Style

@conference{icnc10,
author={Stefan Glüge and Ronald Böck and Andreas Wendemuth},
title={IMPLICIT SEQUENCE LEARNING - A Case Study with a 4–2–4 Encoder Simple Recurrent Network},
booktitle={Proceedings of the International Conference on Fuzzy Computation and 2nd International Conference on Neural Computation - Volume 1: ICNC, (IJCCI 2010)},
year={2010},
pages={279-288},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0003061402790288},
isbn={978-989-8425-32-4},
}


in EndNote Style

TY - CONF
JO - Proceedings of the International Conference on Fuzzy Computation and 2nd International Conference on Neural Computation - Volume 1: ICNC, (IJCCI 2010)
TI - IMPLICIT SEQUENCE LEARNING - A Case Study with a 4–2–4 Encoder Simple Recurrent Network
SN - 978-989-8425-32-4
AU - Glüge S.
AU - Böck R.
AU - Wendemuth A.
PY - 2010
SP - 279
EP - 288
DO - 10.5220/0003061402790288