arXiv · 1807.09527
Adiabatic Superconducting Artificial Neural Network: Basic Cells
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 a one-shot calculation of sigmoid and hyperbolic tangent activation functions most commonly used in MLP. The synapse features by both positive and negative signal transfer coefficients in the range ~ (-0.5,0.5). We briefly discuss implementation issues and further steps toward multilayer adiabatic superconducting artificial neural network which promises to be a compact and the most energy-efficient implementation of MLP.
Explore related subjects
Keep this discovery
Explore connections, maps & timelines
I. I. Soloviev, A. E. Schegolev, N. V. Klenov, S. V. Bakurskiy, M. Yu. Kupriyanov, M. V. Tereshonok, A. V. Shadrin, V. S. Stolyarov, A. A. Golubov. 2018-07-25. Adiabatic Superconducting Artificial Neural Network: Basic Cells. https://doi.org/10.1063/1.5042147
Cite the original work for its findings. Save a collection to share your selection of sources.