Optimisation challenge for superconducting adiabatic neural network implementing XOR and OR boolean functions

TL;DR

This paper presents a novel design of superconducting adiabatic neural networks using Josephson cells, employing gradient descent for parameter optimization, successfully implementing XOR and OR functions.

Contribution

It introduces a new approach for tuning superconducting neural networks with Josephson cells using gradient descent, enabling efficient logical operation implementation.

Findings

Successful implementation of XOR and OR functions

Efficient parameter adjustment via gradient descent

Potential for superconducting neural network applications

Abstract

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.