Advertisement

A Brainmorphic Computing Hardware Paradigm Through Complex Nonlinear Dynamics

  • Yoshihiko HorioEmail author
Conference paper
Part of the Understanding Complex Systems book series (UCS)

Abstract

In a brainmorphic computing paradigm, a hardware system should process information imitating the anatomical and physiological mechanisms of the brain by naturally using physical and dynamical characteristics of the constituent devices, especially through nonlinear analog circuits and devices. The latest knowledge from brain science, especially, on high-order brain functions emerged from high-dimensional complex neuro-dynamics, are reflected in the design of brainmorphic hardware. In addition, the bodily and environmental constraints are considered and utilized as embodiment in this hardware paradigm. In this paper, we propose a brain/body whole organism computation paradigm where brain-intrinsic efficient and distinct information-processing styles and functions are expected to emerge through high-dimensional complex nonlinear dynamics and the embodiment. In particular, we employ a chaotic neuron in a reservoir neural network to emerge the reference-self in the brain/body whole organism computing framework. Chaotic behavior is usually avoided in the reservoir computing because it will violate the echo state property. However, we deliberately introduce high-dimensional chaotic dynamics through the chaotic neurons, but preserving the echo state property. The high-dimensional chaotic dynamics create a rich variety of neural patterns, and at the same time, integrate information in the neural patterns into a unique dynamical state as a high-dimensional attractor. We show preliminary results for chaotic time-series predictions through the chaotic reservoir neural network to demonstrate feasibility of the chaotic dynamics introduced in the reservoir.

Notes

Acknowledgements

This work is supported by JSPS KAKENHI Grant Numbers 16K00340 and 17H0693, and the Cooperative Research Project Program of the Research Institute of Electrical Communication, Tohoku University.

References

  1. 1.
    A. Damasio, Feeling of What Happens (Harcourt Brace, 1999). ISBN 0156010755Google Scholar
  2. 2.
    G. Edelman, G. Tononi, A Universe of Consciousness (Basic Books, 2000). ISBN 0465013775Google Scholar
  3. 3.
    A. Damasio, Self Comes to Mind –Constructing the Conscious Brain– (Pantheon, 2010). ISBN: 13: 9780307378750Google Scholar
  4. 4.
    J. Hawkins, What intelligent machines need to learn from the neocortex. IEEE Spectr. 54(6), 33–37; 68–69 (2017)CrossRefGoogle Scholar
  5. 5.
    Y. Horio, Towards a neuromorphic computing hardware system, in Proceedings of International Symposium on Nonlinear Theory and Its Applications (2017), pp. 189–192Google Scholar
  6. 6.
    Y. Horio, Towards a brainmorphic computing paradigm and a brain/body whole organism computation system, in Proceedings of RISP International Workshop on Nonlinear Circuits, Communicaltion and Signal Processing (2017), pp. 703–706Google Scholar
  7. 7.
    C. Mead, Neuromorphic electronic systems. Proc. IEEE 78(10), 1629–1636 (1990)CrossRefGoogle Scholar
  8. 8.
    M. Lukos̆evic̆ius, H. Jaeger, Reservior computing approaches to recurrent neural network training. Comput. Sci. Rev. 3, 127–149 (2009)Google Scholar
  9. 9.
    Y. Horio, K. Aihara, Analog computation through high-dimensional physical chaotic neuro-dynamics. Physica-D 237(9), 1215–1225 (2008)MathSciNetCrossRefGoogle Scholar
  10. 10.
    Z.F. Mainen, T.J. Sejnowski, Reliability of spike timing in neocortical neurons. Science 268, 1503–1506 (1995)CrossRefGoogle Scholar
  11. 11.
    A. Uchida, R. McAllister, R. Roy, Consistency of nonlinear system response to complex drive signals. Phy. Rev. Lett. 93, 244102 (2004)Google Scholar
  12. 12.
    K. Kaneko, I. Tsuda, Chaotic itinerancy. AIP Chaos 13(3), 926–936 (2003)MathSciNetCrossRefGoogle Scholar
  13. 13.
    K. Aihara, T. Takabe, M. Toyoda, Chaotic neural networks. Phy. Rev. Lett. A 144, 333–340 (1990)MathSciNetCrossRefGoogle Scholar

Copyright information

© Springer Nature Switzerland AG 2019

Authors and Affiliations

  1. 1.Research Institute of Electrical CommunicationTohoku UniversitySendaiJapan

Personalised recommendations