Online Training of a Photonic Reservoir Computer

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


This chapter presents an experiment that was not originally planned as part of my thesis. The project was set up when Michiel Hermans joined our team in 2015 with an idea of implementing the backpropagation training algorithm in hardware, using our opto-electronic reservoir computer with one slight modification. We found that, compared when the backpropagation algorithm is not used, the error rate of the resulting computing device, evaluated on three benchmark tasks, decreases considerably. This demonstrates that electro-optical analog computers can embody a large part of their own training process, allowing them to be applied to new, more difficult tasks.


  1. 1.
    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.Google Scholar
  2. 2.
    Vandoorne, Kristof, Wouter Dierckx, Benjamin Schrauwen, David Verstreten, Roel Baets, Peter Bienstman, and Jan Van Campenhout. 2008. Toward optical signal processing using photonic reservoir computing. Optics Express 16: 11182–11192.ADSCrossRefGoogle Scholar
  3. 3.
    Appeltant, Lennert, Miguel Cornelles Soriano, Guy Van der Sande, Jan Danckaert, Serge Massar, Joni Dambre, Benjamin Schrauwen, Claudio R Mirasso, and Ingo Fischer. 2011. Information processing using a single dynamical node as complex system. Nature Communications 2: 468.ADSCrossRefGoogle Scholar
  4. 4.
    Paquot, Yvan, François Duport, Anteo Smerieri, Joni Dambre, Benjamin Schrauwen, Marc Haelterman, and Serge Massar. 2012. Optoelectronic reservoir computing. Scientific Reports 2: 287.Google Scholar
  5. 5.
    Larger, Laurent, M.C. Soriano, Daniel Brunner, L. Appeltant, Jose M. Gutiérrez, Luis Pesquera, Claudio R. Mirasso, and Ingo Fischer. 2012. Photonic informtion processing beyond Turing: an optoelectronic implementation of reservoir computing. Optics Express 20: 3241–3249.ADSCrossRefGoogle Scholar
  6. 6.
    Martinenghi, Romain, Sergei Rybalko, Maxime Jacquot, Yanne Kouomou Chembo, and Laurent Larger. 2012. Photonic nonlinear transient computing with multiple-delay wavelength dynamics. Physical Review Letters 108: 244101.Google Scholar
  7. 7.
    Duport, François, Bendix Schneider, Anteo Smerieri, Marc Haelterman, and Serge Massar. 2012. All-optical reservoir computing. Optics Express 20: 22783–22795.ADSCrossRefGoogle Scholar
  8. 8.
    Brunner, Daniel, Miguel C Soriano, Claudio R Mirasso, and Ingo Fischer. 2013. Parallel photonic information processing at gigabyte per second data rates using transient states. Nature Communications 4: 1364ADSCrossRefGoogle Scholar
  9. 9.
    Dejonckheere, Antoine, François Duport, Anteo Smerieri, Li Fang, Jean-Louis Oudar, Marc Haelterman, and Serge Massar. 2014. All-optical reservoir computer based on saturation of absorption. Optics Express 22: 10868–10881.ADSCrossRefGoogle Scholar
  10. 10.
    Vandoorne, Kristof, Pauline Mechet, Thomas Van Vaerenbergh, Martin Fiers, Geert Morthier, David Verstraeten, Benjamin Schrauwen, Joni Dambre, and Peter Bienstman. Experimental demonstration of reservoir computing on a silicon photonics chip. Nature Communications 5: 3541.Google Scholar
  11. 11.
    Bishop, Christopher M. 2006. Pattern recognition and machine learning. SpringerGoogle Scholar
  12. 12.
    Haykin, Simon. 2000. Adaptive filter theory. Upper Saddle River, New Jersey: Prentice-Hall.zbMATHGoogle Scholar
  13. 13.
    Bottou, Léon. 1998. Online algorithms and stochastic approximations. Online Learning and Neural Networks. Cambridge University PressGoogle Scholar
  14. 14.
    Vinckier, Quentin, Françcois Duport, Anteo Smerieri, Kristof Vandoorne, Peter Bienstman, Marc Haelterman, and Serge Massar. 2015. High-performance photonic reservoir computer based on a coherently driven passive cavity. Optica 2 (5): 438–446.CrossRefGoogle Scholar
  15. 15.
    Duport, François, Anteo Smerieri, Akram Akrout, Marc Haelterman, and Serge Massar. 2016. Fully analogue photonic reservoir computer. Scientific Reports 6: 22381.Google Scholar
  16. 16.
    Benedetto, Sergio, and Ezio Biglieri. 1999. Principles of digital transmission: With wireless applications. Springer Science & Business Media.Google Scholar
  17. 17.
    Singh, Jaspreet, Sandeep Ponnuru, and Upamanyu Madhow. 2009. Multigig bit communication: The ADC bottleneck. In IEEE international conference on ultra-wideband, 2009. ICUWB 2009, 22–27. IEEEGoogle Scholar
  18. 18.
    Sobel, David Amory, and Robert W. Brodersen. 2009. A 1 Gb/s mixed-signal baseband analog front-end for a 60 GHz wireless receiver. IEEE Journal of Solid-State Circuits 44 (4): 1281–1289.CrossRefGoogle Scholar
  19. 19.
    Feng, Xiaodong, Guanghui He, and Jun Ma. 2010. A new approach to reduce the resolution requirement of the ADC for high data rate wireless receivers. In 2010 IEEE 10th international conference on signal processing (ICSP), 1565–1568. IEEEGoogle Scholar
  20. 20.
    Yong, Su-Khiong, Pengfei Xia, and Alberto Valdes-Garcia. 2011. 60 GHz technology for Gbps WLAN and WPAN: From theory to practice. WileyGoogle Scholar
  21. 21.
    Hassan, Khursheed, Theodore S Rappaport, and Jeffrey G Andrews. 2010. Analog equalization for low power 60 GHz receivers in realistic multipath channels. In Global telecommunications conference (GLOBE–COM 2010), 2010 IEEE, 1–5. IEEEGoogle Scholar
  22. 22.
    Malone, Jerry, and Mark A Wickert. 2011. Practical volterra equalizers for wideband satellite communications with twta nonlinearities. In Digital signal processing workshop and IEEE signal processing education workshop (DSP/SPE), 2011 IEEE., 48–53. IEEEGoogle Scholar
  23. 23.
    Bauduin, Marc, Anteo Smerieri, Serge Massar, and François Horlin. 2015. Equalization of the non-linear satellite communication channel with an echo state network. In vehicular technology conference (VTC Spring), 2015 IEEE 81st, 1–5. IEEEGoogle Scholar
  24. 24.
    Mathews, V John, and Lee Junghsi. 1994. Adaptive algorithms for bilinear filtering. In SPIE’s 1994 international symposium on optics, imaging, and instrumentation. international society for optics and photonics, 317–327.Google Scholar
  25. 25.
    Arfken, George B. 1985. Mathematical methods for physicists. Orlando, FL: Academic PressCrossRefGoogle Scholar
  26. 26.
    IEEE Standard VHDL Language Reference Manual. 1994. In: ANSI/IEEE Std 1076-1993.Google Scholar
  27. 27.
    Pedroni, Volnei A. 2004. Pedroni. Circuit Design with VHDL: MIT Press.Google Scholar
  28. 28.
    Virtex-6 FPGA DSP48E1 Slice. 2011. UG369. Xilinx Inc.Google Scholar
  29. 29.
    Wang, Jingjing, Hao Zhang, Tingting Lv, and T Aaron Gulliver. 2012. Capacity of 60 GHz wireless communication systems over fading channels. Journal of Networks 7.1: 203–209.Google Scholar
  30. 30.
    Duarte, Melissa, Ashutosh Sabharwal, Vaneet Aggarwal, Rittwik Jana, KK Ramakrishnan, Christopher W Rice, and NK Shankaranarayanan. 2014. Design and characterization of a full-duplex multiantenna system for WiFi networks. In IEEE transactions on vehicular technology vol 63.3, 1160–1177.CrossRefGoogle Scholar
  31. 31.
    Jaeger, Herbert, and Harald Haas. 2004. Harnessing nonlinearity: Predicting chaotic systems and saving energy in wireless communication. Science 304: 78–80.ADSCrossRefGoogle Scholar
  32. 32.
    Antonik, Piotr, François Duport, Anteo Smerieri, Michiel Hermans, Marc Haelterman, and Serge Massar. 2015. Online training of an optoelectronic reservoir computer. In APNNA’s 22th international conference on neural information processing. Vol. 9490, 233–240. LNCSGoogle Scholar
  33. 33.
    Hermans, Michiel, Joni Dambre, and Peter Bienstman. 2015. Optoelectronic systems trained with backpropagation through time. IEEE Transactions on Neural Networks and Learning Systems 26 (7): 1545–1550.MathSciNetCrossRefGoogle Scholar
  34. 34.
    Hermans, Michiel, Miguel Soriano, Joni Dambre, Peter Bienstman, and Ingo Fischer. 2015. Photonic delay systems as machine learning implementations. JMLR 16: 2081–2097.MathSciNetzbMATHGoogle Scholar
  35. 35.
    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

Copyright information

© Springer International Publishing AG, part of Springer Nature 2018

Authors and Affiliations

  1. 1.CentraleSupélecMetzFrance

Personalised recommendations