THE HIERARCHICAL MAP FORMING MODEL

Luis Eduardo Rodriguez Soto, Cheng-Yuan Liou

2006

Abstract

In the present paper we propose a motor control model inspired by organizational priciples of the cerebral cortex. Specifically the model is based on cortical maps and functional hierarchy in sensory and motor areas of the brain. Self-Organizing Maps (SOM) have proven to be useful in modeling cortical topological maps (Palakal et al., 1995). A hierarchical SOM provides a natural way to extract hierarchical information from the environment, which we propose may in turn be used to select actions hierarchically. We use a neighborhood update version of the Q-learning algorithm, so the final model maps a continuous input space to a continuous action space in a hierarchical, topology preserving manner. The model is called the Hierarchical Map Forming model (HMF) due to the way in which it forms maps in both the input and output spaces in a hierarchical manner.

References

  1. Holroyd, C.B. Coles, M. (2002). The Neural Basis of Human Error Processing: Reinforcement Learning, Dopamine, and the Error-Related Negativity Psychological Review. Vol. 109, No. 4, 679-709.
  2. Kohonen, T. (2001). Self-Organizing Maps. Springer Verlag, Heidelberg, Germany.
  3. Koikkalainen, P. and Oja, E. (1990). Self-organizing hierarchical feature maps. In Proceedings of International Joint Conference on Neural Networks (IJCNN'90) Information Systems.
  4. Millan , J. Possenato, D. Dedieu, E. (2002). ContinuousAction Q-Learning. Machine Learning. Springer, Netherlands .
  5. Muakkassa, K. F., Strick, P. L. (1979). Frontal Lobe Inputs to Primate Motor Cortex. Evidence for Four Somatotopically Organized ”Premotor” Areas. Brain Research. Elsevier/North-Holland Biomedical Press.
  6. Oja, E. and Kaski ,S. (1979). Kohonen Maps. Elsevier Science, Netherlands.
  7. Palakal, M.J. Murthy, U. Chittajallu, S.K. Wong, D. (1995). Tonotopic Representation of Auditory Responses Using Self-Organizing Maps. Mathematical and Computer Modelling. Elsevier Science, Netherlands.
  8. Smith, A.J. (2001). Applications of the self-organising map to reinforcement learning. Neural Networks. Elsevier, United States
  9. Simon Haykin. (1999). Neural Networks. Prentice-Hall, New Jersey, Second Edition.
  10. Watkins,C. Dayan,C. (1992). Technical Note: Q-Learning. Machine Learning. Springer, Netherlands.
  11. Wolpert, D. Kawato, M. (1998). Multiple Paired Forward and Inverse Models for Motor Control. Neural Networks. Elsevier, United States
Download


Paper Citation


in Harvard Style

Eduardo Rodriguez Soto L. and Liou C. (2006). THE HIERARCHICAL MAP FORMING MODEL . In Proceedings of the Third International Conference on Informatics in Control, Automation and Robotics - Volume 1: ICINCO, ISBN 978-972-8865-59-7, pages 167-172. DOI: 10.5220/0001221801670172


in Bibtex Style

@conference{icinco06,
author={Luis Eduardo Rodriguez Soto and Cheng-Yuan Liou},
title={THE HIERARCHICAL MAP FORMING MODEL},
booktitle={Proceedings of the Third International Conference on Informatics in Control, Automation and Robotics - Volume 1: ICINCO,},
year={2006},
pages={167-172},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0001221801670172},
isbn={978-972-8865-59-7},
}


in EndNote Style

TY - CONF
JO - Proceedings of the Third International Conference on Informatics in Control, Automation and Robotics - Volume 1: ICINCO,
TI - THE HIERARCHICAL MAP FORMING MODEL
SN - 978-972-8865-59-7
AU - Eduardo Rodriguez Soto L.
AU - Liou C.
PY - 2006
SP - 167
EP - 172
DO - 10.5220/0001221801670172