Theory of a superconducting artificial neuron for extended backpropagation learning algorism

  • Authors

    • Haruna Katayama
    • Toshiyuki Fujii
    • Noriyuki Hatakenaka
    2018-08-24
    https://doi.org/10.14419/ijet.v7i3.29.18551
  • Artificial Neural Networks, Superconducting Quantum Interference Devices (SQUID), Sigmoid Function, Superconducting Neurons.

  • Abstract

    An artificial neuron using superconducting devices, so-called double SQUID, applicable to the extended backpropagation learning algorism is studied. It is shown that the tunable slope of the sigmoid function required in the algorism can be achieved under the fixed temperature by externally applied magnetic fields threading the ring with two Josephson junctions in the double SQUID.

     

     

  • References

    1. [1] F. Rosenblatt, Principles of Neurodynamics: Perceptrons and the Theory of Brain Mechanisms (Spartan Books, Washington, 1962).

      [2] D. E. Rumelhart, G. E. Hinton, and R. J. Williams, “Learning representations by back-propagating errors,†Nature, vol. 323, pp. 533–536, October 1986.

      [3] A. Sperduti and A. Starita, “Speed up learning and network optimization with extended back propagation,†Neural Networks, vol. 6, pp. 365-383, 1993.

      [4] Y. Harada and E. Goto, “Artificial neural network circuits with Josephson devices,†IEEE Transactions on Magnetics, vol. 27, pp. 2863–2866, March 1991.

      [5] M. Hidaka and L. A. Akers, “An artificial neural cell implemented with superconducting circuits,†Superconductor Science and Technology, vol. 4, pp. 654-657, November 1991.

      [6] Y. Mizugaki, K. Nakajima, Y. Sawada, and T. Yamashita, “Superconducting neural circuits using fluxon pulses,†Applied Physics Letters, vol. 62, pp. 762–764, February 1993.

      [7] Y. Mizugaki, K. Nakajima, Y. Sawada, and T. Yamashita, “Implementation of new superconducting neural circuits using coupled squids,†IEEE Transactions on Applied Superconductivity, vol. 4, pp. 1–8, May 1994.

      [8] T. V. Filippov, Y. A. Polyakov, V. K. Semenov, and K. K. Likharev, “Signal resolution of RSFQ comparators,†IEEE Transactions on Applied Superconductivity, vol. 5, pp. 2240–2243, June 1995.

      [9] Y. Yamanashi, K. Umeda, and N. Yoshikawa, “Pseudo sigmoid function generator for a superconductive neural network,†IEEE Trans. on Applied Superconductivity, vol. 23, pp. 1701004, June 2003.

      [10] A. E. Schegolev, N. V. Klenov, I. I. Soloviev, and M. V. Tereshonok, “Adiabatic superconducting cells for ultra-low-power artificial neural networks,†Beilstein J Nanotechnol, vol. 7, pp. 1397–1403, October 2016.

      [11] Submitted to publication.

  • Downloads

  • How to Cite

    Katayama, H., Fujii, T., & Hatakenaka, N. (2018). Theory of a superconducting artificial neuron for extended backpropagation learning algorism. International Journal of Engineering & Technology, 7(3.29), 170-172. https://doi.org/10.14419/ijet.v7i3.29.18551

    Received date: 2018-08-29

    Accepted date: 2018-08-29

    Published date: 2018-08-24