Photonic Reservoir Computing Based on Laser Dynamics with External Feedback

  • Seiji Takeda
  • Daiju Nakano
  • Toshiyuki Yamane
  • Gouhei Tanaka
  • Ryosho Nakane
  • Akira Hirose
  • Shigeru Nakagawa
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 9947)

Abstract

Reservoir computing is a novel paradigm of neural network, offering advantages in low learning cost and ease of implementation as hardware. In this paper we propose a concept of reservoir computing consisting of a semiconductor laser subject to external feedback by a mirror, where input signal is supplied as modulation pattern of mirror reflectivity. In that system, non-linear interaction between optical field and electrons are enhanced in complex manner under substantial external feedback, leading to achieve highly nonlinear projection of input electric signal to output optical field intensity. It is exhibited that the system can most efficiently classify waveforms of sequential input data when operating around laser oscillation’s effective threshold.

Keywords

Reservoir computing Recurrent neural network Sequential data processing Laser Silicon photonics Energy efficiency 

References

  1. 1.
    Quoc, V.L.: Building high-level features using large scale unsupervised learning. In: 2013 IEEE International Conference on Acoustic, Speech and Signal Processing, pp. 8595–8598, Vancouver, BC (2016)Google Scholar
  2. 2.
    Taigman, Y., Yang, M., Ranzato, M.A., Wolf, L.: Deep face: closing the gap to human-level performance in face verification. In: 2014 IEEE Conference on Computer Vision and Pattern Recognition, pp. 1701–1708 (2014)Google Scholar
  3. 3.
    Wang, W., Arora, R., Livescu, K., Bilmes, J.: On deep multi-view representation learning. In: Proceedings of the 32nd International Conference on Machine Learning, pp. 1083–1092 (2015)Google Scholar
  4. 4.
    Jaeger, H., Haas, H.: Harnessing nonlinearity: predicting chaotic systems and saving energy in wireless communication. Science 304, 78–80 (2004)CrossRefGoogle Scholar
  5. 5.
    Maass, W., Natschläger, T., Markram, H.: Real-time computing without stable states: a new framework for neural computation based on perturbations. Neural Comput. 14, 2531–2560 (2002)CrossRefMATHGoogle Scholar
  6. 6.
    Verstraeten, D., Schrauwen, B., Stroobandt, D.: Isolated word recognition using a liquid state machine. In: Proceedings of the 13th European Symposium on Artificial Neural Networks (ESANN), pp. 435–440 (2005)Google Scholar
  7. 7.
    Jalalvand, A., Wallendael, G.V., Walle R.V.: Real-time reservoir computing network-based systems for detection tasks on visual contents. In: 7th International Conference on Computational Intelligence, Communication Systems and Networks (CICSyN), pp. 146–151 (2015)Google Scholar
  8. 8.
    Triefenbach, F., Jalalvand, A., Schrauwen, B., Martens, J.-P.: Phoneme recognition with large hierarchical reservoirs. Adv. Neural Inf. Process. Syst. 23, 2307–2315 (2010)Google Scholar
  9. 9.
    Yamane, T., Katayama, Y., Nakane, R., Tanaka, G., Nakano, D.: Wave-based reservoir computing by synchronization of coupled oscillators. In: Arik, S., Huang, T., Lai, W.K., Liu, Q. (eds.) ICONIP 2015. LNCS, vol. 9491, pp. 198–205. Springer, Heidelberg (2015). doi:10.1007/978-3-319-26555-1_23 CrossRefGoogle Scholar
  10. 10.
    Appeltant, L., Soriano, M.C., Van der Sande, G., Danchaert, J., Massar, S., Dambre, J., Schrauwen, B., Mirasso, C.R., Fischer, I.: Information processing using a single dynamical node as complex system. Nature Commun. 2, 468–472 (2011)CrossRefGoogle Scholar
  11. 11.
    Nakajima, K., Hauser, H., Li, T., Pfeifers, R.: Information processing via physical soft body. Sci. Rep. 5, 10487 (2015)CrossRefGoogle Scholar
  12. 12.
    Vandoorne, K., Dierckx, W., Schrauwen, B., Verstraeten, D., Baets, R., Bienstman, P., Campenhout, J.V.: Toward optical signal processing using photonic reservoir computing. Opt. Express 16, 1182–1192 (2008)CrossRefGoogle Scholar
  13. 13.
    Brunner, D., Soriano, M.C., Mirasso, C.R., Fischer, I.: Parallel photonic information processing at gigabyte per second data rates using transient state. Nature Commun. 4, 1364 (2012)CrossRefGoogle Scholar
  14. 14.
    Vlasov, Y.: Silicon integrated nanophotonics: From fundamental science to manufacturable technology. http://spie.org/newsroom/pw15_plenary_landing/pw15_plenary_vlasov
  15. 15.
    Sciamanna, M., Shore, K.A.: Physics and applications of laser diode chaos. Nat. Photonics 9, 151–162 (2015)CrossRefGoogle Scholar
  16. 16.
    Kannno, K., Uchida, A.: Complexity analysis in a semiconductor laser with time-delayed optical feedback. Rev. Laser Eng. 39, 543–549 (2011)CrossRefGoogle Scholar
  17. 17.
    Sukow, D.W., Gauhier, D.J.: Entraining power-dropout events in an external-cavity semiconductor laser using weak modulation of the injection current. IEEE J. Quantum Electron. 36, 175–183 (2000)CrossRefGoogle Scholar

Copyright information

© Springer International Publishing AG 2016

Authors and Affiliations

  • Seiji Takeda
    • 1
  • Daiju Nakano
    • 1
  • Toshiyuki Yamane
    • 1
  • Gouhei Tanaka
    • 2
  • Ryosho Nakane
    • 2
  • Akira Hirose
    • 2
  • Shigeru Nakagawa
    • 1
  1. 1.IBM Research – TokyoKawasakiJapan
  2. 2.Graduate School of EngineeringThe University of TokyoTokyoJapan

Personalised recommendations