Waveform Classification by Memristive Reservoir Computing

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


Reservoir computing is one of the computational frameworks based on recurrent neural networks for learning sequential data. We study the memristive reservoir computing where a network of memristors, instead of recurrent neural networks, provides a nonlinear mapping from input sequential signals to high-dimensional spatiotemporal dynamics. First we formulate the circuit equations of the memristive networks and describe the simulation methods. Then we use the memristive reservoir computing for solving a waveform classification problem. We demonstrate how the classification ability depends on the number of reservoir outputs and the variability of the memristive elements. Our methods are useful for finding a better architecture of the memristive reservoir under the inevitable element variability when implemented with nano/micro-scale devices.


Reservoir computing Recurrent networks Memristors Pattern classification Energy efficiency 



This work was partially supported by JSPS KAKENHI Grant Number 16K00326 (GT).


  1. 1.
    Schrauwen, B., Verstraeten, D., Van Campenhout, J.: An overview of reservoir computing: theory, applications and implementations. In: Proceedings of the 15th European Symposium on Artificial Neural Networks, pp. 471–482 (2007)Google Scholar
  2. 2.
    Verstraeten, D., Schrauwen, B., d’Haene, M., Stroobandt, D.: An experimental unification of reservoir computing methods. Neural Netw. 20(3), 391–403 (2007)CrossRefMATHGoogle Scholar
  3. 3.
    Jaeger, H.: The “echo state” approach to analysing and training recurrent neural networks-with an erratum note. Bonn, Germany: German National Research Center for Information Technology GMD Technical report 148, 34 (2001)Google Scholar
  4. 4.
    Jaeger, H.: Tutorial on training recurrent neural networks, covering BPPT, RTRL, EKF and the “echo state network” approach. GMD-Forschungszentrum Informationstechnik (2002)Google Scholar
  5. 5.
    Maass, W., Natschlager, T., Markram, H.: Real-time computing without stable states: a new framework for neural computation based on perturbations. Neural Comput. 14(11), 2531–2560 (2002)CrossRefMATHGoogle Scholar
  6. 6.
    Di Ventra, M., Pershin, Y.V., Chua, L.O.: Circuit elements with memory: memristors, memcapacitors, and meminductors. Proc. IEEE 97(10), 1717–1724 (2009)CrossRefGoogle Scholar
  7. 7.
    Chua, L.: Memristor-the missing circuit element. IEEE Trans. Circ. Theory 18(5), 507–519 (1971)CrossRefGoogle Scholar
  8. 8.
    Strukov, D.B., Snider, G.S., Stewart, D.R., Williams, R.S.: The missing memristor found. Nature 453(7191), 80–83 (2008)CrossRefGoogle Scholar
  9. 9.
    Chua, L.O., Kang, S.M.: Memristive devices and systems. Proc. IEEE 64(2), 209–223 (1976)CrossRefMathSciNetGoogle Scholar
  10. 10.
    Chang, T., Yang, Y., Lu, W.: Building neuromorphic circuits with memristive devices. IEEE Circ. Syst. Mag. 13(2), 56–73 (2013)CrossRefGoogle Scholar
  11. 11.
    Kulkarni, M.S., Teuscher, C.: Memristor-based reservoir computing. In: 2012 IEEE/ACM International Symposium on Nanoscale Architectures (NANOARCH), pp. 226–232 (2012)Google Scholar
  12. 12.
    Bürger, J., Teuscher, C.: Variation-tolerant computing with memristive reservoirs. In: Proceedings of the 2013 IEEE/ACM International Symposium on Nanoscale Architectures, pp. 1–6. IEEE Press (2013)Google Scholar
  13. 13.
    Bürger, J., Goudarzi, A., Stefanovic, D., Teuscher, C.: Hierarchical composition of memristive networks for real-time computing. In: 2015 IEEE/ACM International Symposium on Nanoscale Architectures (NANOARCH), pp. 33–38. IEEE (2015)Google Scholar
  14. 14.
    Burger, J., Goudarzi, A., Stefanovic, D., Teuscher, C.: Computational capacity and energy consumption of complex resistive switch networks. AIMS Mater. Sci. 2(4), 530–545 (2015)CrossRefGoogle Scholar
  15. 15.
    Merkel, C., Saleh, Q., Donahue, C., Kudithipudi, D.: Memristive reservoir computing architecture for epileptic seizure detection. Procedia Comput. Sci. 41, 249–254 (2014)CrossRefGoogle Scholar
  16. 16.
    Stieg, A.Z., Avizienis, A.V., Sillin, H.O., Martin-Olmos, C., Aono, M., Gimzewski, J.K.: Emergent criticality in complex turing B-type atomic switch networks. Adv. Mater. 24(2), 286–293 (2012)CrossRefGoogle Scholar
  17. 17.
    Sillin, H.O., Aguilera, R., Shieh, H.H., Avizienis, A.V., Aono, M., Stieg, A.Z., Gimzewski, J.K.: A theoretical and experimental study of neuromorphic atomic switch networks for reservoir computing. Nanotechnology 24(38), 384004 (2013)CrossRefGoogle Scholar
  18. 18.
    Stieg, A.Z., Avizienis, A.V., Sillin, H.O., Aguilera, R., Shieh, H.-H., Martin-Olmos, C., Sandouk, E.J., Aono, M., Gimzewski, J.K.: Self-organization and emergence of dynamical structures in neuromorphic atomic switch networks. In: Adamatzky, A., Chua, L. (eds.) Memristor Networks, pp. 173–209. Springer, Cham (2014). doi: 10.1007/978-3-319-02630-5_10 CrossRefGoogle Scholar
  19. 19.
    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
  20. 20.
    Joglekar, Y.N., Wolf, S.J.: The elusive memristor: properties of basic electrical circuits. Eur. J. Phys. 30(4), 661 (2009)CrossRefMATHGoogle Scholar
  21. 21.
    McDonald, N.R., Pino, R.E., Rozwood, P.J., Wysocki, B.T.: Analysis of dynamic linear and non-linear memristor device models for emerging neuromorphic computing hardware design. In: The 2010 International Joint Conference on Neural Networks (IJCNN), pp. 1–5. IEEE (2010)Google Scholar
  22. 22.
    Fei, W., Yu, H., Zhang, W., Yeo, K.S.: Design exploration of hybrid CMOS and memristor circuit by new modified nodal analysis. IEEE Trans. Very Large Scale Integr. (VLSI) Syst. 20(6), 1012–1025 (2012)CrossRefGoogle Scholar
  23. 23.
    MATLAB: version 9.0 (R2016a). The MathWorks Inc., Natick, Massachusetts (2016)Google Scholar
  24. 24.
    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
  25. 25.
    Katayama, Y., Yamane, T., Nakano, D., Nakane, R., Tanaka, G.: Wave-based neuromorphic computing framework for brain-like energy efficiency and integration. IEEE Trans. Nanotechnol. 15(5), 762–769 (2016)CrossRefGoogle Scholar
  26. 26.
    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
  27. 27.
    Rodan, A., Tino, P.: Minimum complexity echo state network. IEEE Trans. Neural Netw. 22(1), 131–144 (2011)CrossRefGoogle Scholar
  28. 28.
    Watts, D.J., Strogatz, S.H.: Collective dynamics of “small-world” networks. Nature 393(6684), 440–442 (1998)CrossRefMATHGoogle Scholar

Copyright information

© Springer International Publishing AG 2017

Authors and Affiliations

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

Personalised recommendations