Journal of Applied Physics, volume 124, issue 15, pages 152113

Adiabatic superconducting artificial neural network: Basic cells

Soloviev Igor I 1, 2, 3
Schegolev Andrey E. 2, 3, 4, 5
Klenov Nikolay V. 2, 3, 4, 5, 6
Bakurskiy Sergey V 1, 2, 3
Tereshonok M.V. 2, 4
Stolyarov V. S. 1, 6, 7, 8
Publication typeJournal Article
Publication date2018-09-26
Quartile SCImago
Q2
Quartile WOS
Q2
Impact factor3.2
ISSN00218979, 10897550
General Physics and Astronomy
Abstract
We consider adiabatic superconducting cells operating as an artificial neuron and synapse of a multilayer perceptron (MLP). Their compact circuits contain just one and two Josephson junctions, respectively. While the signal is represented as magnetic flux, the proposed cells are inherently nonlinear and close-to-linear magnetic flux transformers. The neuron is capable of providing the one-shot calculation of sigmoid and hyperbolic tangent activation functions most commonly used in MLP. The synapse features both positive and negative signal transfer coefficients in the range ∼ ( − 0.5 , 0.5 ). We briefly discuss implementation issues and further steps toward the multilayer adiabatic superconducting artificial neural network, which promises to be a compact and the most energy-efficient implementation of MLP.We consider adiabatic superconducting cells operating as an artificial neuron and synapse of a multilayer perceptron (MLP). Their compact circuits contain just one and two Josephson junctions, respectively. While the signal is represented as magnetic flux, the proposed cells are inherently nonlinear and close-to-linear magnetic flux transformers. The neuron is capable of providing the one-shot calculation of sigmoid and hyperbolic tangent activation functions most commonly used in MLP. The synapse features both positive and negative signal transfer coefficients in the range ∼ ( − 0.5 , 0.5 ). We briefly discuss implementation issues and further steps toward the multilayer adiabatic superconducting artificial neural network, which promises to be a compact and the most energy-efficient implementation of MLP.

Citations by journals

1
2
3
4
5
6
7
Beilstein Journal of Nanotechnology
Beilstein Journal of Nanotechnology, 7, 14.89%
Beilstein Journal of Nanotechnology
7 publications, 14.89%
IEEE Transactions on Applied Superconductivity
IEEE Transactions on Applied Superconductivity, 5, 10.64%
IEEE Transactions on Applied Superconductivity
5 publications, 10.64%
Superconductor Science and Technology
Superconductor Science and Technology, 4, 8.51%
Superconductor Science and Technology
4 publications, 8.51%
Nanomaterials
Nanomaterials, 3, 6.38%
Nanomaterials
3 publications, 6.38%
Journal of Applied Physics
Journal of Applied Physics, 3, 6.38%
Journal of Applied Physics
3 publications, 6.38%
Physical Review B
Physical Review B, 2, 4.26%
Physical Review B
2 publications, 4.26%
Symmetry
Symmetry, 2, 4.26%
Symmetry
2 publications, 4.26%
Journal of Physics: Conference Series
Journal of Physics: Conference Series, 2, 4.26%
Journal of Physics: Conference Series
2 publications, 4.26%
JETP Letters
JETP Letters, 2, 4.26%
JETP Letters
2 publications, 4.26%
Applied Physics Letters
Applied Physics Letters, 2, 4.26%
Applied Physics Letters
2 publications, 4.26%
Nanobiotechnology Reports
Nanobiotechnology Reports, 1, 2.13%
Nanobiotechnology Reports
1 publication, 2.13%
Computational Mathematics and Mathematical Physics
Computational Mathematics and Mathematical Physics, 1, 2.13%
Computational Mathematics and Mathematical Physics
1 publication, 2.13%
Low Temperature Physics
Low Temperature Physics, 1, 2.13%
Low Temperature Physics
1 publication, 2.13%
Laser Physics Letters
Laser Physics Letters, 1, 2.13%
Laser Physics Letters
1 publication, 2.13%
Nano Letters
Nano Letters, 1, 2.13%
Nano Letters
1 publication, 2.13%
Journal of Physics Condensed Matter
Journal of Physics Condensed Matter, 1, 2.13%
Journal of Physics Condensed Matter
1 publication, 2.13%
ACM Computing Surveys
ACM Computing Surveys, 1, 2.13%
ACM Computing Surveys
1 publication, 2.13%
Coatings
Coatings, 1, 2.13%
Coatings
1 publication, 2.13%
Condensed Matter
Condensed Matter, 1, 2.13%
Condensed Matter
1 publication, 2.13%
Physics of Metals and Metallography
Physics of Metals and Metallography, 1, 2.13%
Physics of Metals and Metallography
1 publication, 2.13%
Physical Review Applied
Physical Review Applied, 1, 2.13%
Physical Review Applied
1 publication, 2.13%
Journal of Communications Technology and Electronics
Journal of Communications Technology and Electronics, 1, 2.13%
Journal of Communications Technology and Electronics
1 publication, 2.13%
Journal of Experimental and Theoretical Physics
Journal of Experimental and Theoretical Physics, 1, 2.13%
Journal of Experimental and Theoretical Physics
1 publication, 2.13%
Communications Physics
Communications Physics, 1, 2.13%
Communications Physics
1 publication, 2.13%
1
2
3
4
5
6
7

Citations by publishers

1
2
3
4
5
6
7
8
IOP Publishing
IOP Publishing, 8, 17.02%
IOP Publishing
8 publications, 17.02%
Pleiades Publishing
Pleiades Publishing, 7, 14.89%
Pleiades Publishing
7 publications, 14.89%
Multidisciplinary Digital Publishing Institute (MDPI)
Multidisciplinary Digital Publishing Institute (MDPI), 7, 14.89%
Multidisciplinary Digital Publishing Institute (MDPI)
7 publications, 14.89%
Beilstein-Institut
Beilstein-Institut, 7, 14.89%
Beilstein-Institut
7 publications, 14.89%
American Institute of Physics (AIP)
American Institute of Physics (AIP), 6, 12.77%
American Institute of Physics (AIP)
6 publications, 12.77%
IEEE
IEEE, 5, 10.64%
IEEE
5 publications, 10.64%
American Physical Society (APS)
American Physical Society (APS), 3, 6.38%
American Physical Society (APS)
3 publications, 6.38%
American Chemical Society (ACS)
American Chemical Society (ACS), 1, 2.13%
American Chemical Society (ACS)
1 publication, 2.13%
Association for Computing Machinery (ACM)
Association for Computing Machinery (ACM), 1, 2.13%
Association for Computing Machinery (ACM)
1 publication, 2.13%
Springer Nature
Springer Nature, 1, 2.13%
Springer Nature
1 publication, 2.13%
1
2
3
4
5
6
7
8
  • We do not take into account publications that without a DOI.
  • Statistics recalculated only for publications connected to researchers, organizations and labs registered on the platform.
  • Statistics recalculated weekly.
Metrics
Share
Cite this
GOST |
Cite this
GOST Copy
Soloviev I. I. et al. Adiabatic superconducting artificial neural network: Basic cells // Journal of Applied Physics. 2018. Vol. 124. No. 15. p. 152113.
GOST all authors (up to 50) Copy
Soloviev I. I., Schegolev A. E., Klenov N. V., Bakurskiy S. V., Kupriyanov M. Yu., Tereshonok M., Shadrin A. V., Stolyarov V. S., Golubov A. A. Adiabatic superconducting artificial neural network: Basic cells // Journal of Applied Physics. 2018. Vol. 124. No. 15. p. 152113.
RIS |
Cite this
RIS Copy
TY - JOUR
DO - 10.1063/1.5042147
UR - https://doi.org/10.1063%2F1.5042147
TI - Adiabatic superconducting artificial neural network: Basic cells
T2 - Journal of Applied Physics
AU - Soloviev, Igor I
AU - Schegolev, Andrey E.
AU - Klenov, Nikolay V.
AU - Bakurskiy, Sergey V
AU - Kupriyanov, Mikhail Yu
AU - Tereshonok, M.V.
AU - Shadrin, Anton V
AU - Stolyarov, V. S.
AU - Golubov, Alexander A
PY - 2018
DA - 2018/09/26 00:00:00
PB - American Institute of Physics (AIP)
SP - 152113
IS - 15
VL - 124
SN - 0021-8979
SN - 1089-7550
ER -
BibTex |
Cite this
BibTex Copy
@article{2018_Soloviev,
author = {Igor I Soloviev and Andrey E. Schegolev and Nikolay V. Klenov and Sergey V Bakurskiy and Mikhail Yu Kupriyanov and M.V. Tereshonok and Anton V Shadrin and V. S. Stolyarov and Alexander A Golubov},
title = {Adiabatic superconducting artificial neural network: Basic cells},
journal = {Journal of Applied Physics},
year = {2018},
volume = {124},
publisher = {American Institute of Physics (AIP)},
month = {sep},
url = {https://doi.org/10.1063%2F1.5042147},
number = {15},
pages = {152113},
doi = {10.1063/1.5042147}
}
MLA
Cite this
MLA Copy
Soloviev, Igor I., et al. “Adiabatic superconducting artificial neural network: Basic cells.” Journal of Applied Physics, vol. 124, no. 15, Sep. 2018, p. 152113. https://doi.org/10.1063%2F1.5042147.
Found error?