Complex-Valued Neural Networks for Wave-Based Realization of Reservoir Computing

  • Akira Hirose
  • Seiji Takeda
  • Toshiyuki Yamane
  • Daiju Nakano
  • Shigeru Nakagawa
  • Ryosho Nakane
  • Gouhei Tanaka
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 10637)


In this paper, we discuss the significance of complex-valued neural-network (CVNN) framework in energy-efficient neural networks, in particular in wave-based reservoir networks. Physical-wave reservoir networks are highly enhanced by CVNNs. From this viewpoint, we also compare the features of reservoir computing and other architectures.


Neural hardware Complex-valued neural networks (CVNN) 


  1. 1.
    Takeda, S., Nakano, D., Yamane, T., Tanaka, G., Nakane, R., Hirose, A., Nakagawa, S.: Photonic reservoir computing based on laser dynamics with external feedback. In: Hirose, A., Ozawa, S., Doya, K., Ikeda, K., Lee, M., Liu, D. (eds.) ICONIP 2016. LNCS, vol. 9947, pp. 222–230. Springer, Cham (2016). doi: 10.1007/978-3-319-46687-3_24 CrossRefGoogle Scholar
  2. 2.
    Yamane, T., Takeda, S., Nakano, D., Tanaka, G., Nakane, R., Nakagawa, S., Hirose, A.: Dynamics of reservoir computing at the edge of stability. In: Hirose, A., Ozawa, S., Doya, K., Ikeda, K., Lee, M., Liu, D. (eds.) ICONIP 2016. LNCS, vol. 9947, pp. 205–212. Springer, Cham (2016). doi: 10.1007/978-3-319-46687-3_22 CrossRefGoogle Scholar
  3. 3.
    Tanaka, G., Nakane, R., Yamane, T., Nakano, D., Takeda, S., Nakagawa, S., Hirose, A.: Exploiting Heterogeneous units for reservoir computing with simple architecture. In: Hirose, A., Ozawa, S., Doya, K., Ikeda, K., Lee, M., Liu, D. (eds.) ICONIP 2016. LNCS, vol. 9947, pp. 187–194. Springer, Cham (2016). doi: 10.1007/978-3-319-46687-3_20 CrossRefGoogle Scholar
  4. 4.
    Mori, R., Tanaka, G., Nakane, R., Hirose, A., Aihara, K.: Computational performance of echo state networks with dynamic synapses. In: Hirose, A., Ozawa, S., Doya, K., Ikeda, K., Lee, M., Liu, D. (eds.) ICONIP 2016. LNCS, vol. 9947, pp. 264–271. Springer, Cham (2016). doi: 10.1007/978-3-319-46687-3_29 CrossRefGoogle Scholar
  5. 5.
    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, Cham (2015). doi: 10.1007/978-3-319-26555-1_23 CrossRefGoogle Scholar
  6. 6.
    Hirose, A., Eckmiller, R.: Proposal of frequency-domain multiplexing in optical neural networks. Neurocomputing 10(2), 197–204 (1996)CrossRefGoogle Scholar
  7. 7.
    Hirose, A., Eckmiller, R.: Coherent optical neural networks that have optical-frequency-controlled behavior and generalization ability in the frequency domain. Appl. Opt. 35(5), 836–843 (1996)CrossRefGoogle Scholar
  8. 8.
    Kawata, S., Hirose, A.: Coherent optical neural network that learns desirable phase values in frequency domain by using multiple optical-path differences. Opt. Lett. 28(24), 2524–2526 (2003)CrossRefGoogle Scholar
  9. 9.
    Kawata, S., Hirose, A.: Frequency-multiplexed logic circuit based on a coherent optical neural network. Appl. Opt. 44(19), 4053–4059 (2005)CrossRefGoogle Scholar
  10. 10.
    Kawata, S., Hirose, A.: Frequency-multiplexing ability of complex-valued Hebbian learning in logic gates. Int. J. Neural Syst. 12(1), 43–51 (2008)Google Scholar
  11. 11.
    Tanizawa, K., Hirose, A.: Performance analysis of steepest-descent-based feedback control of tunable dispersion compensator for adaptive dispersion compensation in all-optical dynamic routing networks. IEEE/OSA J. Lightwave Technol. 25(4), 1086–1094 (2007)CrossRefGoogle Scholar
  12. 12.
    Tanizawa, K., Hirose, A.: Fast tracking algorithm for adaptive compensation of high-speed PMD variation caused by SOP change in milliseconds. IEEE Photonics Technol. Lett. 21(3), 140–142 (2009)CrossRefGoogle Scholar
  13. 13.
    Hara, T., Hirose, A.: Adaptive plastic-landmine visualizing radar system: effects of aperture synthesis and feature-vector dimension reduction. IEICE Trans. Electron. E88–C(12), 2282–2288 (2005)CrossRefGoogle Scholar
  14. 14.
    Suksmono, A.B., Hirose, A.: Interferometric sar image restoration using Monte-Carlo metropolis method. IEEE Trans. Sig. Process. 50(2), 290–298 (2002)CrossRefGoogle Scholar
  15. 15.
    Shang, F., Hirose, A.: Quaternion neural-network-based PolSAR land classification in poincare-sphere-parameter space. IEEE Trans. Geosci. Remote Sens. 52(9), 5693–5703 (2014)CrossRefGoogle Scholar
  16. 16.
    Ding, T., Hirose, A.: Fading channel prediction based on combination of complex-valued neural networks and chirp Z-transform. IEEE Trans. Neural Netw. Learn. Syst. 25(9), 1686–1695 (2014)CrossRefGoogle Scholar
  17. 17.
    Hirose, A.: Complex-Valued Neural Networks, 2nd edn. Springer, Heidelberg (2012)CrossRefMATHGoogle Scholar
  18. 18.
    Hirose, A., Eckmiller, R.: Behavior control of coherent-type neural networks by carrier-frequency modulation. IEEE Trans. Neural Netw. 7(4), 1032–1034 (1996)CrossRefGoogle Scholar
  19. 19.
    Hirose, A., Kiuchi, M.: Coherent optical associative memory system that processes complex-amplitude information. IEEE Photon. Tech. Lett. 12(5), 564–566 (2000)CrossRefGoogle Scholar
  20. 20.
    Goto, E.: The parametron - a new circuit element which utilizes non-linear reactors. Paper of Technical Group of Electronic Computers and Nonlinear Theory, IECE (1954, in Japanese)Google Scholar
  21. 21.
    Hirose, A.: Complex-Valued Neural Networks: Theories and Applications. Innovative Intelligence, vol. 5. World Scientific Publishing, Singapore (2003)CrossRefMATHGoogle Scholar
  22. 22.
    Hirose, A. (ed.): Complex-Valued Neural Networks: Advances and Applications. IEEE Press Series on Computational Intelligence. IEEE Press and Wiley, New Jersey (2013)Google Scholar
  23. 23.
    Mandic, D.P., Goh, V.S.L.: Complex Valued Nonlinear Adaptive Filters - Noncircularity, Widely Linear and Neural Models. Wiley, Hoboken (2009)CrossRefMATHGoogle Scholar
  24. 24.
    Adali, T., Haykin, S.: Adaptive Signal Processing: Next Generation Solutions. Wiley-IEEE Press, New Jersey (2010)CrossRefGoogle Scholar
  25. 25.
    Aizenberg, I.: Complex-Valued Neural Networks with Multi-Valued Neurons. Studies in Computational Intelligence. Springer, Heidelberg (2011)CrossRefMATHGoogle Scholar
  26. 26.
    Nitta, T.: Complex-Valued Neural Networks: Utilizing High-Dimensional Parameters. Information Science Reference, Pennsylvania (2009)Google Scholar
  27. 27.
    Bayro-Corrochano, E.: Geometric Computing for Wavelet Transforms, Robot Vision, Learning, Control and Action. Springer, Heidelberg (2010)MATHGoogle Scholar
  28. 28.
    Suresh, S., Sundararajan, N., Savitha, R.: Supervised Learning with Complex-valued Neural Networks. Springer, Heidelberg (2013)CrossRefGoogle Scholar
  29. 29.
    Hirose, A., Higo, T., Tanizawa, K.: Efficient generation of holographic movies with frame interpolation using a coherent neural network. IEICE Electron. Expr. 3(19), 417–423 (2006)CrossRefGoogle Scholar
  30. 30.
    Tay, C.S., Tanizawa, K., Hirose, A.: Error reduction in holographic movies using a hybrid learning method in coherent neural networks. Appl. Opt. 47(28), 5221–5228 (2008)CrossRefGoogle Scholar
  31. 31.
    Takeda, M., Kirihara, S., Miyamoto, Y., Sakoda, K., Honda, K.: Localization of electromagnetic waves in three dimensional fractal cavities. Phys. Rev. Lett. 92, 093902 (2004)CrossRefGoogle Scholar
  32. 32.
    Ono, A., Sato, S., Kinjo, M., Nakajima, K.: Study on the performance of neuromorphic adiabatic quantum computation algorithms. In: International Joint Conference on Neural Networks (IJCNN) 2008, Hong Kong, Nakajima, pp. 2508–2512, June 2008Google Scholar
  33. 33.
    Hirose, A., Yoshida, S.: Generalization characteristics of complex-valued feedforward neural networks in relation to signal coherence. IEEE Trans. Neural Netw. Learn. Syst. 23, 541–551 (2012)CrossRefGoogle Scholar
  34. 34.
    Antonik, P., Duport, F., Smerieri, A., Hermans, M., Haelterman, M., Massar, S.: Online training of an opto-electronic reservoir computer. In: Arik, S., Huang, T., Lai, W.K., Liu, Q. (eds.) ICONIP 2015. LNCS, vol. 9490, pp. 233–240. Springer, Cham (2015). doi: 10.1007/978-3-319-26535-3_27 CrossRefGoogle Scholar
  35. 35.
    Matsui, N., Isokawa, T., Kusamichi, H., Peper, F., Nishimura, H.: Quaternion neural network with geometrical operators. J. Intell. Fuzzy Syst. 15, 149–164 (2004)MATHGoogle Scholar
  36. 36.
    Takizawa, Y., Shang, F., Hirose, A.: Adaptive land classification and new class generation by unsupervised double-stage learning in poincare sphere space for polarimetric synthetic aperture radars. Neurocomputing 248, 3–10 (2017)CrossRefGoogle Scholar

Copyright information

© Springer International Publishing AG 2017

Authors and Affiliations

  • Akira Hirose
    • 1
  • Seiji Takeda
    • 2
  • Toshiyuki Yamane
    • 2
  • Daiju Nakano
    • 2
  • Shigeru Nakagawa
    • 2
  • Ryosho Nakane
    • 1
  • Gouhei Tanaka
    • 1
  1. 1.Social Cooperation Program on Energy Efficient Information Processing (EEIP) and Department of Electrical Engineering and Information SystemsThe University of TokyoTokyoJapan
  2. 2.IBM Research - TokyoTokyoJapan

Personalised recommendations