Simple Feature Quantities for Learning of Dynamic Binary Neural Networks

  • Ryuji Sato
  • Toshimichi SaitoEmail author
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 9489)


This paper presents simple feature quantities for learning of dynamic binary neural networks. The teacher signal is a binary periodic orbit corresponding to control signal of switching circuits. The feature quantities characterize generation of spurious memories and stability of the teacher signal. We present a simple greedy search based algorithm where the two feature quantities are used as cost functions. Performing basic numerical experiments, the algorithm efficiency is confirmed.


Dynamic neural networks Greedy search Switching circuits 


  1. 1.
    Kouzuki, R., Saito, T.: Learning of simple dynamic binary neural networks. IEICE Trans. Fundam. E96–A(8), 1775–1782 (2013)CrossRefGoogle Scholar
  2. 2.
    Moriyasu, J., Saito, T.: Sparsification and stability of simple dynamic binary neural networks. IEICE Trans. Fundam. E97–A(4), 985–988 (2014)CrossRefGoogle Scholar
  3. 3.
    Nakayama, Y., Kouzuki, R., Saito, T.: Application of the dynamic binary neural network to switching circuits. In: Lee, M., Hirose, A., Hou, Z.-G., Kil, R.M. (eds.) ICONIP 2013, Part II. LNCS, vol. 8227, pp. 697–704. Springer, Heidelberg (2013) CrossRefGoogle Scholar
  4. 4.
    Moriyasu, J., Saito, T.: A deep dynamic binary neural network and its application to matrix converters. In: Wermter, S., Weber, C., Duch, W., Honkela, T., Koprinkova-Hristova, P., Magg, S., Palm, G., Villa, A.E.P. (eds.) ICANN 2014. LNCS, vol. 8681, pp. 611–618. Springer, Heidelberg (2014) Google Scholar
  5. 5.
    Moriyasu, J., Saito, T.: A cascade system of simple dynamic binary neural networks and its sparsification. In: Loo, C.K., Yap, K.S., Wong, K.W., Teoh, A., Huang, K. (eds.) ICONIP 2014, Part I. LNCS, vol. 8834, pp. 231–238. Springer, Heidelberg (2014) Google Scholar
  6. 6.
    Gray, D.L., Michel, A.N.: A training algorithm for binary feed forward neural networks. IEEE Trans. Neural Netw. 3(2), 176–194 (1992)CrossRefGoogle Scholar
  7. 7.
    Chen, F., Chen, G., He, Q., He, G., Xu, X.: Universal perceptron and DNA-like learning algorithm for binary neural networks: non-LSBF implementation. IEEE Trans. Neural Netw. 20(8), 1293–1301 (2009)CrossRefGoogle Scholar
  8. 8.
    Chua, L.O.: A Nonlinear Dynamics Perspective of Wolfram’s New Kind of Science, I and II. World Scientific, Singapore (2005) Google Scholar
  9. 9.
    Wada, W., Kuroiwa, J., Nara, S.: Completely reproducible description of digital sound data with cellular automata. Phys. Lett. A 306, 110–115 (2002)MathSciNetCrossRefzbMATHGoogle Scholar
  10. 10.
    Rosin, P.L.: Training cellular automata for image processing. IEEE Trans. Image Process. 15(7), 2076–2087 (2006)CrossRefGoogle Scholar
  11. 11.
    Iguchi, T., Hirata, A., Torikai, H.: Theoretical and heuristic synthesis of digital spiking neurons for spike-pattern-division multiplexing. IEICE Trans. Fundam. E93–A(8), 1486–1496 (2010)CrossRefGoogle Scholar
  12. 12.
    Bose, B.K.: Neural network applications in power electronics and motor drives - an introduction and perspective. IEEE Trans. Ind. Electron. 54(1), 14–33 (2007)CrossRefGoogle Scholar
  13. 13.
    Rodriguez, J., Rivera, M., Kolar, J.W., Wheeler, P.W.: A review of control and modulation methods for matrix converters. ieee tie 59(1), 58–70 (2012)Google Scholar
  14. 14.
    Araki, K., Saito, T.: An associative memory including time-variant self-feedback. Neural Netw. 7(8), 1267–1271 (1994)CrossRefGoogle Scholar

Copyright information

© Springer International Publishing Switzerland 2015

Authors and Affiliations

  1. 1.Hosei UniversityKoganeiJapan

Personalised recommendations