Advertisement

Towards Online-Trained Analogue Readout Layer

  • Piotr AntonikEmail author
Chapter
Part of the Springer Theses book series (Springer Theses)

Abstract

This chapter presents the last project that I started with the OPERA-Photonique group. We proposes the use of online training in the context of analogue readout layers for photonic reservoir computers. We studied the applicability of this method using numerical simulations of an experimentally feasible reservoir computer with an analogue readout layer. We also considered a nonlinear output layer, which would be very difficult to train with traditional methods. We show numerically that online learning allows to circumvent the added complexity of the analogue layer and obtain the same level of performance as with a digital layer.

References

  1. 1.
    Smerieri, Anteo, François Duport, Yvan Paquot, Benjamin Schrauwen,Marc Haelterman, and Serge Massar. 2012. Analog readout for optical reservoir computers. In Advances in neural information processing systems, pp. 944–952.Google Scholar
  2. 2.
    Duport, François, Anteo Smerieri, Akram Akrout, Marc Haelterman, and Serge Massar. 2016. Fully analogue photonic reservoir computer. Scientific Reports 6: 22381.ADSCrossRefGoogle Scholar
  3. 3.
    Vinckier, Quentin, Arno Bouwens, Marc Haelterman, and Serge Massar. 2016. Autonomous all-photonic processor based on reservoir computing paradigm. In Conference on lasers and electro-optics. Optical society of America, SF1F.1.Google Scholar
  4. 4.
    Antonik, Piotr, Marc Haelterman, and Serge Massar. 2017. Online training for high-performance analogue readout layers in photonic reservoir computers. Cognitive Computation 9: 297–306.CrossRefGoogle Scholar
  5. 5.
    Woods, Damien, and Thomas J. Naughton. 2012. Optical computing: Photonic neural networks. Nature Physics 8 (4): 257–259.ADSCrossRefGoogle Scholar
  6. 6.
    Léon, Bottou. 1998. Online algorithms and stochastic approximations. In Online learning and neural networks: Cambridge University Press.zbMATHGoogle Scholar
  7. 7.
    Shalev-Shwartz, Shai. 2012. Online learning and online convex optimization. Foundations and Trends in Machine Learning 4 (2): 107–194.CrossRefGoogle Scholar
  8. 8.
    Antonik, Piotr, François Duport, Michiel Hermans, Anteo Smerieri, Marc Haelterman, and Serge Massar. 2017. Online training of an opto-electronic reservoir computer applied to real-time channel equalization. IEEE Transactions on Neural Networks and Learning Systems 28 (11): 2686–2698.CrossRefGoogle Scholar
  9. 9.
    Horowitz, Paul, and Winfield Hill. 1980. The art of electronics. Cambridge University Press.Google Scholar
  10. 10.
    Tikhonov, Andrei Nikolaevich, A.V. Goncharsky, V.V. Stepanov, and Anatoly G. Yagola. 1995. Numerical methods for the solution of ill-posed problems, vol. 328. Netherlands: Springer.CrossRefGoogle Scholar
  11. 11.
    Paquot, Yvan, François Duport, Anteo Smerieri, Joni Dambre, Benjamin Schrauwen, Marc Haelterman, and Serge Massar. 2012. Optoelectronic reservoir computing. Scientific Reports 2: 287.ADSCrossRefGoogle Scholar
  12. 12.
    Antonik, Piotr, Marc Haelterman, and Serge Massar. 2017. Brain-inspired photonic signal processor for generating periodic patterns and emulating chaotic systems. Physical Review Applied 7: 054014.ADSCrossRefGoogle Scholar
  13. 13.
    Soriano, Miguel C., Silvia Ortín, Daniel Brunner, C.R. Laurent Larger, Ingo Fischer Mirasso, and Luıs Pesquera. 2013. Optoelectronic reservoir computing: Tackling noise-induced performance degradation. Optics Express 21 (1): 12–20.ADSCrossRefGoogle Scholar
  14. 14.
    Soriano, Miguel C., Silvia Ortín, Lars Keuninckx, Lennert Appeltant, Jan Danckaert, Luis Pesquera, and Guy Van der Sande. 2015. Delay-based reservoir computing: Noise effects in a combined analog and digital implementation. IEEE Transactions on Neural Networks and Learning Systems 26 (2): 388–393.MathSciNetCrossRefGoogle Scholar
  15. 15.
    Antonik, Piotr, Michiel Hermans, François Duport, Marc Haelterman, and Serge Massar. 2016. Towards pattern generation and chaotic series prediction with photonic reservoir computers. In SPIE’s 2016 laser technology and industrial laser conference, vol. 9732, 97320B.Google Scholar
  16. 16.
    Duport, François, Bendix Schneider, Anteo Smerieri, Marc Haelterman, and Serge Massar. 2012. All-optical reservoir computing. Optics Express 20: 22783–22795.ADSCrossRefGoogle Scholar
  17. 17.
    Vinckier, Quentin, François Duport, Anteo Smerieri, Kristof Vandoorne, Peter Bienstman, Marc Haelterman, and Serge Massar. 2015. High-performance 142 Chapter V. Towards online-trained analogue readout layer photonic reservoir computer based on a coherently driven passive cavity. Optica 2 (5): 438–446.Google Scholar
  18. 18.
    Bauduin, Marc, Quentin Vinckier, Serge Massar, and François Horlin. 2016. High performance bio-inspired analog equalizer for DVB-S2 nonlinear communication channel. In 2016 IEEE 17th international workshop on Signal Processing advances in wireless communications (SPAWC), pp. 1–5. IEEE.Google Scholar

Copyright information

© Springer International Publishing AG, part of Springer Nature 2018

Authors and Affiliations

  1. 1.CentraleSupélecMetzFrance

Personalised recommendations