Optimisation Challenge for a Superconducting Adiabatic Neural Network That Implements XOR and OR Boolean Functions.

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 a system that implements XOR and OR logical operations.

A bifunctional superconducting cell as flux qubit and neuron.

Josephson digital or analog ancillary circuits are an essential part of a large number of modern quantum processors. The natural candidate for the basis of tuning, coupling, and neromorphic co-processing elements for processors based on flux qubits is the adiabatic (reversible) superconducting logic cell. Using the simplest implementation of such a cell as an example, we have investigated the conditions under which it can optionally operate as an auxiliary qubit while maintaining its "classical" neural functionality. The performance and temperature regime estimates obtained confirm the possibility of practical use of a single-contact inductively shunted interferometer in a quantum mode in adjustment circuits for q-processors.

A superconducting adiabatic neuron in a quantum regime.

We explore the dynamics of an adiabatic neural cell of a perceptron artificial neural network in a quantum regime. This mode of cell operation is assumed for a hybrid system of a classical neural network whose configuration is dynamically adjusted by a quantum co-processor. Analytical and numerical studies take into account non-adiabatic processes as well as dissipation, which leads to smoothing of quantum coherent oscillations. The obtained results indicate the conditions under which the neuron possesses the required sigmoid activation function.