In this article, we consider designs of simple analog artificial neural networks based on adiabatic Josephson cells with a sigmoid activation function. A new approach based on the gradient descent method is developed to adjust the circuit parameters, allowing efficient signal transmission between the network layers. The proposed solution is demonstrated on the example of the system implementing XOR and OR logical operations.
Cite
@article{arxiv.2405.03521,
title = {Optimisation challenge for superconducting adiabatic neural network implementing XOR and OR boolean functions},
author = {D. S. Pashin and M. V. Bastrakova and D. A. Rybin and I. I. Soloviev and A. E. Schegolev and N. V. Klenov},
journal= {arXiv preprint arXiv:2405.03521},
year = {2024}
}