Abstract
This study shows how sensory-action sequences of imitating finite state machines (FSMs) can be learned by utilizing the deterministic dynamics of recurrent neural networks (RNNs). Our experiments indicated that each possible combinatorial sequence can be recalled by specifying its respective initial state value and also that fractal structures appear in this initial state mapping after the learning converges. We also observed that the RNN dynamics evolves, going back and forth between regions of window and chaos in the learning process, and that the evolved dynamical structure turns out to be structurally stable after adding a negligible amount of noise.
Keywords
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.
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
J. Tanji and K. Shima. Role for supplementary motor area cells in planning several movements ahead. Nature, 371:413–416, 1994.
D. Wolpert and M. Kawato. Multiple paired forward and inverse models for motor control. Neural Networks, 11:1317–1329, 1998.
M.I. Jordan. Attractor dynamics and parallelism in a connectionist sequential machine. In Proc. of Eighth Annual Conference of Cognitive Science Society, pages 531–546. Hillsdale, NJ: Erlbaum, 1986.
J.L. Elman. Finding structure in time. Cognitive Science, 14:179–211, 1990.
J.B. Pollack. The induction of dynamical recognizers. Machine Learning, 7:227–252, 1991.
J.F. Kolen. Exploring the computational capabilities of recurrent neural networks. PhD thesis, The Ohio State University, 1994.
C.L. Giles, G.Z. Sun, H.H. Chen, Y.C. Lee, and D. Chen. Higher order recurrent networks and grammatical inference. In D.S. Touretzky, editor, Advances in Neural Information Processing Systems 2, pages 380–387. San Mateo, CA: Morgan Kaufmann, 1990.
D.E. Rumelhart, G.E. Hinton, and R.J. Williams. Learning internal representations by error propagation. In D.E. Rumelhart and J.L. Mclelland, editors, Parallel Distributed Processing. Cambridge, MA: MIT Press, 1986.
M.I. Jordan and D.E. Rumelhart. Forward models: supervised learning with a distal teacher. Cognitive Science, 16:307–354, 1992.
B. l. Hao. Elementary Symbolic Dynamic and Chaos in Dissipative System. Singapore: World Scientific, 1989.
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2003 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Nishimoto, R., Tani, J. (2003). Learning to Generate Combinatorial Action Sequences Utilizing the Initial Sensitivity of Deterministic Dynamical Systems. In: Mira, J., Álvarez, J.R. (eds) Computational Methods in Neural Modeling. IWANN 2003. Lecture Notes in Computer Science, vol 2686. Springer, Berlin, Heidelberg. https://doi.org/10.1007/3-540-44868-3_54
Download citation
DOI: https://doi.org/10.1007/3-540-44868-3_54
Published:
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-40210-7
Online ISBN: 978-3-540-44868-6
eBook Packages: Springer Book Archive