A NOVEL ADAPTIVE CONTROL VIA SIMPLE RULE(S) USING CHAOTIC DYNAMICS IN A RECURRENT NEURAL NETWORK MODEL AND ITS HARDWARE IMPLEMENTATION

Ryosuke Yoshinaka, Masato Kawashima, Yuta Takamura, Hitoshi Yamaguchi, Naoya Miyahara, Kei-ichiro Nabeta, Yongtao Li, Shigetoshi Nara

2010

Abstract

A novel idea of adaptive control via simple rule(s) using chaotic dynamics in a recurrent neural network model is proposed. Since chaos in brain was discovered, an important question, what is the functional role of chaos in brain, has been arising. Standing on a functional viewpoint of chaos, the authors have been proposing that chaos has complex functional potentialities and have been showing computer experiments to solve many kinds of ”ill-posed problems”, such as memory search and so on. The key idea is to harness the onset of complex nonlinear dynamics in dynamical systems. More specifically, attractor dynamics and chaotic dynamics in a recurrent neural network model are introduced via changing a system parameter, ”connectivity”, and adaptive switching between attractor regime and chaotic regime depending surrounding situations is applied to realizing complex functions via simple rule(s). In this report, we will show (1)Global outline of our idea, (2)Several computer experiments to solve 2-dimensional maze by an autonomous robot having a neural network, where the robot can recognize only rough directions of target with uncertainty and the robot has no pre-knowledge about the configuration of obstacles (ill-posed setting), (3)Hardware implementations of the computer experiments using two-wheel or two-legs robots driven by our neuro chaos simulator. Successful results are shown not only in computer experiments but also in practical experiments, (4)Making pseudo-neuron device using semiconductor and opto-electronic technologies, where the device is called ”dynamic self-electro optical effect devices (DSEED)”. They could be ”neuromorphic devices” or even ”brainmorphic devices”.

References

  1. Fujii, H., Itoh, H., Aihara, K., Ichinose, N., and Tsukada, M. (1996). Dynamical cell assembly hypothesistheoretical possibility of spatio-temporal coding in the cortex. In Neural Networks. vol. 9, p. 1303.
  2. Huber, F. and Thorson, H. (1985). Cricket auditory communication. In Sci. Amer. vol. 253, pp. 60-68.
  3. Li, Y. and Nara, S. (2008). Novel tracking function of moving target using chaotic dynamics in a recurrent neural network model. In Cognitive Neurodynamics. vol. 2, pp. 39 - 48.
  4. Mikami, S. and Nara, S. (2003). Dynamical responses of chaotic memory dynamics to weak input in a recurrent neural network model. In Neural Computing. vol. 11, pp. 129-136.
  5. Nara, S. (2003). Can potentially useful dynamics to solve complex problems emerge from constrained chaos and/or chaotic itinerancy? In Chaos. vol. 13, pp. 1110-1121.
  6. Nara, S. and Davis, P. (1992). Chaotic wandering and search in a cycle memory neural network. In Progress of Theoretical Physics. vol. 88, pp. 845-855.
  7. Nara, S., Davis, P., Kawachi, M., and Totuji, H. (1993). Memory search using complex dynamics in a recurrent neural network model. In Neural Networks. vol. 6, pp. 963-973.
  8. Nara, S., Davis, P., Kawachi, M., and Totuji, H. (1995). Chaotic memory dynamics in a recurrent neural network with cycle memories embedded by pseudoinverse method. In Int. J. Bifurcation and Chaos Appl. Sci. Eng. vol. 5, pp. 1205-1212.
  9. Ohkawa, Y., Yamamoto, T., Nagaya, T., and Nara, S. (2005). Dynamic behaviors of coulpled self-electrooptic effec devices. In Appl. Phys. Lett. vol. 86, p. 111107.
  10. Skarda, C. A. and Freeman, W. J. (1987). How brains make chaos in order to make sense of the world. In Behavioral and Brain Sciences. vol. 10, pp. 161-195.
  11. Suemitsu, Y. and Nara, S. (2004). A solution for twodimensional mazes with use of chaotic dynamics in a recurrent neural network model. In Neural Computation. vol. 16, pp. 1943-1957.
  12. Tokuda, I., Nagashima, T., and Aihara, K. (1997). Global bifurcation structure of chaotic neural networks and its application to traveling salesman problems. In Neural Networks. vol. 10, pp. 1673-1690.
  13. Tsuda, I. (2001). Towards an interpretaion of dynamic neural activity in terms of chaotic dynamical systems. In Behavioral and Brain Sciences. vol. 24, pp. 793-847.
Download


Paper Citation


in Harvard Style

Yoshinaka R., Kawashima M., Takamura Y., Yamaguchi H., Miyahara N., Nabeta K., Li Y. and Nara S. (2010). A NOVEL ADAPTIVE CONTROL VIA SIMPLE RULE(S) USING CHAOTIC DYNAMICS IN A RECURRENT NEURAL NETWORK MODEL AND ITS HARDWARE IMPLEMENTATION . 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 145-155. DOI: 10.5220/0003058301450155


in Bibtex Style

@conference{icnc10,
author={Ryosuke Yoshinaka and Masato Kawashima and Yuta Takamura and Hitoshi Yamaguchi and Naoya Miyahara and Kei-ichiro Nabeta and Yongtao Li and Shigetoshi Nara},
title={A NOVEL ADAPTIVE CONTROL VIA SIMPLE RULE(S) USING CHAOTIC DYNAMICS IN A RECURRENT NEURAL NETWORK MODEL AND ITS HARDWARE IMPLEMENTATION },
booktitle={Proceedings of the International Conference on Fuzzy Computation and 2nd International Conference on Neural Computation - Volume 1: ICNC, (IJCCI 2010)},
year={2010},
pages={145-155},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0003058301450155},
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 - A NOVEL ADAPTIVE CONTROL VIA SIMPLE RULE(S) USING CHAOTIC DYNAMICS IN A RECURRENT NEURAL NETWORK MODEL AND ITS HARDWARE IMPLEMENTATION
SN - 978-989-8425-32-4
AU - Yoshinaka R.
AU - Kawashima M.
AU - Takamura Y.
AU - Yamaguchi H.
AU - Miyahara N.
AU - Nabeta K.
AU - Li Y.
AU - Nara S.
PY - 2010
SP - 145
EP - 155
DO - 10.5220/0003058301450155