Skip to main content
Springer Nature Link
Log in

Symbolic Memory of Motion Patterns by an Associative Memory Dynamics with Self-organizing Nonmonotonicity

  • Conference paper
Neural Information Processing (ICONIP 2007)

Part of the book series: Lecture Notes in Computer Science ((LNTCS,volume 4985))

Included in the following conference series:

  • 1599 Accesses

Abstract

We previously proposed a memory system of motion patterns [4] using an assotiative memory model. It forms symbolic representations of motion patterns based on correlations by utilizing bifurcations of attractors depending on the parameter of activation nonmonotonicity. But the parameter had to be chosen appropreately to some degree by manual. We propose here a way to provide the paremeter with self-organizing dynamics along with the retrieval of the associative momory. Attractors of the parameter are discrete states representing the hierarchical correlations of the stored motion patterns.

This is a preview of subscription content, log in via an institution to check access.

Access this chapter

Log in via an institution

Institutional subscriptions

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

Similar content being viewed by others

References

  1. Amari, S.: Neural Theory of Association and Concept-Formation. Biological Cybernetics 26, 175–185 (1977)

    Article  MATH  MathSciNet  Google Scholar 

  2. Griniasty, M., Tsodyks, M.V., Amit, D.J.: Conversion of Temporal Correlations Between Stimuli to Spatial Correlations Between Attractors. Neural Computation 5, 1–17 (1993)

    Article  Google Scholar 

  3. Hopfield, J.J.: Neural networks and physical systems with emergent collective computational abilities. Proceedings of the National Academy of Sciences of U.S.A. 79, 2554–2558 (1982)

    Article  MathSciNet  Google Scholar 

  4. Kadone, H., Nakamura, Y.: Symbolic Memory for Humanoid Robots Using Hierarchical Bifurcations of Attractors in Nonmonotonic Neural Networks. In: Proc. of the 2005 IEEE/RSJ International Conference on Intelligent Robots and Systems, pp. 2900–2905 (2005)

    Google Scholar 

  5. Kadone, H., Nakamura, Y.: Hierarchical Concept Formation in Associative Memory Models and its Application to Memory of Motions for Humanoid Robots. In: 2006 IEEE-RAS International Conference on Humanoid Robots (Humanoids 2006), Genoa, December 4-6, pp. 432–437 (2006)

    Google Scholar 

  6. Kimoto, T., Okada, M.: Mixed States on neural network with structural learning. Neural Networks 17, 103–112 (2004)

    Article  MATH  Google Scholar 

  7. Kohonen, T.: Self-Organized Formation of Topologically Correct Feature Maps. Biological Cybernetics 43, 59–69 (1982)

    Article  MATH  MathSciNet  Google Scholar 

  8. Matsumoto, N., Okada, M., Sugase, Y., Yamane, S.: Neuronal Mechanisms Encoding Global-to-Fine Information in Inferior-Temporal Cortex. Journal of Computational Neuroscience 18, 85–103 (2005)

    Article  MathSciNet  Google Scholar 

  9. Morita, M.: Associative Memory with Nonmonotone Dynamics. Neural Networks 6, 115–126 (1993)

    Article  Google Scholar 

  10. Okada, M., Nakamura, D., Nakamura, Y.: Self-organizing Symbol Acquisition and Motion Generation based on Dynamics-based Information Processing System. In: Proc. of the second International Workshop on Man-Machine Symbiotic Systems, pp. 219–229 (2004)

    Google Scholar 

  11. Omori, T., Mochizuki, A., Mizutani, K., Nishizaki, M.: Emergence of symbolic behavior from brain like memory with dynamic attention. Neural Networks 12, 1157–1172 (1999)

    Article  Google Scholar 

  12. Oztop, E., Chaminade, T., Cheng, G., Kawato, M.: Imitation Bootstrapping: Experiments on a Robotic Hand. In: Proceedings of 2005 IEEE-RAS International Conference on Humanoid Robots (Humanoids 2005), pp. 189–195 (2005)

    Google Scholar 

  13. Shimozaki, M., Kuniyoshi, Y.: Integration of Spatial and Temporal Contexts for Action Recognition by Self Organizing Neural Networks. In: Proc. of the 2003 IEEE/RSJ International Conference on Intelligent Robots and Systems, pp. 2385–2391 (2003)

    Google Scholar 

  14. Sugita, Y., Tani, J.: Learning Semantic Combinatoriality from the Interaction between Linguistic and Behavioral Processes. Adaptive Behavior 13, 33–52 (2005)

    Article  Google Scholar 

Download references

Author information

Authors and Affiliations

  1. Department of Mechano-Informatics Graduate School of Information Science and Technology, University of Tokyo, 7-3-1, Hongo, Bunkyoku, Tokyo, Japan

    Hideki Kadone & Yoshihiko Nakamura

Authors
  1. Hideki Kadone
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Yoshihiko Nakamura
    View author publications

    You can also search for this author in PubMed Google Scholar

Editor information

Masumi Ishikawa Kenji Doya Hiroyuki Miyamoto Takeshi Yamakawa

Rights and permissions

Reprints and permissions

Copyright information

© 2008 Springer-Verlag Berlin Heidelberg

About this paper

Cite this paper

Kadone, H., Nakamura, Y. (2008). Symbolic Memory of Motion Patterns by an Associative Memory Dynamics with Self-organizing Nonmonotonicity. In: Ishikawa, M., Doya, K., Miyamoto, H., Yamakawa, T. (eds) Neural Information Processing. ICONIP 2007. Lecture Notes in Computer Science, vol 4985. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-540-69162-4_22

Download citation

  • DOI: https://doi.org/10.1007/978-3-540-69162-4_22

  • Publisher Name: Springer, Berlin, Heidelberg

  • Print ISBN: 978-3-540-69159-4

  • Online ISBN: 978-3-540-69162-4

  • eBook Packages: Computer ScienceComputer Science (R0)

Publish with us

Policies and ethics