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.
Buying options
Tax calculation will be finalised at checkout
Purchases are for personal use only
Learn about institutional subscriptionsPreview
Unable to display preview. Download preview PDF.
References
Amari, S.: Neural Theory of Association and Concept-Formation. Biological Cybernetics 26, 175–185 (1977)
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)
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)
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)
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)
Kimoto, T., Okada, M.: Mixed States on neural network with structural learning. Neural Networks 17, 103–112 (2004)
Kohonen, T.: Self-Organized Formation of Topologically Correct Feature Maps. Biological Cybernetics 43, 59–69 (1982)
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)
Morita, M.: Associative Memory with Nonmonotone Dynamics. Neural Networks 6, 115–126 (1993)
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)
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)
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)
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)
Sugita, Y., Tani, J.: Learning Semantic Combinatoriality from the Interaction between Linguistic and Behavioral Processes. Adaptive Behavior 13, 33–52 (2005)
Author information
Authors and Affiliations
Editor information
Rights 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)