Skip to main content

Design and Implementation of Pulse-Coupled Phase Oscillators on a Field-Programmable Gate Array for Reservoir Computing

  • Conference paper
  • First Online:
Neural Information Processing (ICONIP 2020)

Part of the book series: Communications in Computer and Information Science ((CCIS,volume 1333))

Included in the following conference series:

Abstract

Reservoir computing (RC) has been viewed as a model of a neurological system. The RC framework constructs a recurrent neural network, which mimics parts of the brain, to solve temporal problems. To construct a neural network inside a reservoir, we adopt the pulse-coupled phase oscillator (PCPO) with neighbor topology connections on a field-programmable gate array (FPGA). Neural spikes for the PCPO are generated by the Winfree model. The low resource consumption of the proposed model in time-series generation tasks was confirmed in an evaluation study. We also demonstrate that on the FPGA, we can expand a 3 \(\times \) 3 PCPO into a 10 \(\times \) 10 PCPO, generate spike behavior, and predict the target signal with a maximum frequency of 418.796 MHz.

Supported by JSPS KAKENHI grant number 17H01798.

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

Access this chapter

Chapter
USD 29.95
Price excludes VAT (USA)
  • Available as PDF
  • Read on any device
  • Instant download
  • Own it forever
eBook
USD 84.99
Price excludes VAT (USA)
  • Available as EPUB and PDF
  • Read on any device
  • Instant download
  • Own it forever
Softcover Book
USD 109.99
Price excludes VAT (USA)
  • Compact, lightweight edition
  • Dispatched in 3 to 5 business days
  • Free shipping worldwide - see info

Tax calculation will be finalised at checkout

Purchases are for personal use only

Institutional subscriptions

References

  1. Tanaka, G., et al.: Recent advances in physical reservoir computing: a review. Neural Netw. 115, 100–123 (2019)

    Article  Google Scholar 

  2. Lukoševičius, M., Jaeger, H.: Reservoir computing approaches to recurrent neural network training. Comput. Sci. Rev. 3(3), 127–149 (2009)

    Article  Google Scholar 

  3. Kuramoto, Y.: Chemical oscillations, waves, and turbulence. Courier Corporation (2003)

    Google Scholar 

  4. Winfree, A.T.: The Geometry of Biological Time. Springer, New York (2001). https://doi.org/10.1007/978-1-4757-3484-3

    Book  MATH  Google Scholar 

  5. Mirollo, R.E., Strogatz, S.H.: Synchronization of pulse-coupled biological oscillators. SIAM J. Appl. Math. 50(6), 1645–1662 (1990)

    Article  MathSciNet  Google Scholar 

  6. Kuramoto, Y.: Collective synchronization of pulse-coupled oscillators and excitable units. Physica D 50(1), 15–30 (1991)

    Article  MathSciNet  Google Scholar 

  7. Izhikevich, E.M.: Dynamical Systems in Neuroscience. MIT Press, Cambridge (2007)

    Google Scholar 

  8. Atuti, D., Kato, N., Nakada, K., Morie, T.: CMOS circuit implementation of a coupled phase oscillator system using pulse modulation approach. In: 2007 18th European Conference on Circuit Theory and Design, pp. 827–830. IEEE (2007)

    Google Scholar 

  9. Matsuzaka, K., Tohara, T., Nakada, K., Morie, T.: Analog CMOS circuit implementation of a pulse-coupled phase oscillator system and observation of synchronization phenomena. Nonlinear Theory Appl. IEICE 3(2), 180–190 (2012)

    Article  Google Scholar 

  10. Matsuzaka, K., Tanaka, H., Ohkubo, S., Morie, T.: VLSI implementation of coupled MRF model using pulse-coupled phase oscillators. Electron. Lett. 51(1), 46–48 (2014)

    Article  Google Scholar 

  11. Suedomi, Y., Tamukoh, H., Tanaka, M., Matsuzaka, K., Morie, T.: Parameterized digital hardware design of pulse-coupled phase oscillator model toward spike-based computing. In: Lee, M., Hirose, A., Hou, Z.-G., Kil, R.M. (eds.) ICONIP 2013. LNCS, vol. 8228, pp. 17–24. Springer, Heidelberg (2013). https://doi.org/10.1007/978-3-642-42051-1_3

    Chapter  Google Scholar 

  12. Suedomi, Y., Tamukoh, H., Matsuzaka, K., Tanaka, M., Morie, T.: Parameterized digital hardware design of pulse-coupled phase oscillator networks. Neurocomputing 165, 54–62 (2015)

    Article  Google Scholar 

  13. Pramanta, D., Morie, T., Tamukoh, H.: Implementation of multi-FPGA communication using pulse-coupled phase oscillators. In: Proceedings of 2017 International Conference on Artificial Life And Robotics (ICAROB 2017), pp. 128–131 (2017)

    Google Scholar 

  14. Honda, K., Tamukoh, H.: A hardware-oriented echo state network and its FPGA implementation. J. Robot. Netw. Artif. Life (2020)

    Google Scholar 

  15. Pramanta, D., Morie, T., Tamukoh, H.: Synchronization of pulse-coupled phase oscillators over multi-FPGA communication links. J. Robot. Netw. Artif. Life 4(1), 91–96 (2017)

    Article  Google Scholar 

  16. Pramanta, D., Tamukoh, H.: High-speed synchronization of pulse-coupled phase oscillators on multi-FPGA. In: Gedeon, T., Wong, K.W., Lee, M. (eds.) ICONIP 2019. CCIS, vol. 1143, pp. 318–329. Springer, Cham (2019). https://doi.org/10.1007/978-3-030-36802-9_34

    Chapter  Google Scholar 

  17. Katori, Y., Morie, T., Tamukoh, H.: Reservoir computing based on dynamics of pseudo-billiard system in hypercube. In: International Joint Conference on Neural Networks (IJCNN 2019) (2019)

    Google Scholar 

Download references

Acknowledgment

This research is supported by JSPS KAKENHI grant number 17H01798. This paper was partly based on results obtained from a project commissioned by the New Energy and Industrial Technology Development Organization (NEDO), Japan.

Author information

Authors and Affiliations

Authors

Corresponding author

Correspondence to Dinda Pramanta .

Editor information

Editors and Affiliations

Rights and permissions

Reprints and permissions

Copyright information

© 2020 Springer Nature Switzerland AG

About this paper

Check for updates. Verify currency and authenticity via CrossMark

Cite this paper

Pramanta, D., Tamukoh, H. (2020). Design and Implementation of Pulse-Coupled Phase Oscillators on a Field-Programmable Gate Array for Reservoir Computing. In: Yang, H., Pasupa, K., Leung, A.CS., Kwok, J.T., Chan, J.H., King, I. (eds) Neural Information Processing. ICONIP 2020. Communications in Computer and Information Science, vol 1333. Springer, Cham. https://doi.org/10.1007/978-3-030-63823-8_39

Download citation

  • DOI: https://doi.org/10.1007/978-3-030-63823-8_39

  • Published:

  • Publisher Name: Springer, Cham

  • Print ISBN: 978-3-030-63822-1

  • Online ISBN: 978-3-030-63823-8

  • eBook Packages: Computer ScienceComputer Science (R0)

Publish with us

Policies and ethics