Artificial Neural Network based on SQUIDs: demonstration of network training and operation

TL;DR

This paper demonstrates a superconducting quantum interference device (SQUID)-based artificial neural network capable of training and operation, with potential applications in astrophysics, high-energy physics, and medical imaging.

Contribution

It introduces a novel SQUID-based neural network scheme and experimentally demonstrates its ability to perform XOR operations and be trained with examples.

Findings

Successfully tested a small SQUID neural network implementing XOR

Demonstrated training of the network using example data

Proposed scheme is suitable for superconducting applications

Abstract

We propose a scheme for the realization of artificial neural networks based on Superconducting Quantum Interference Devices (SQUIDs). In order to demonstrate the operation of this scheme we designed and successfully tested a small network that implements a XOR gate and is trained by means of examples. The proposed scheme can be particularly convenient as support for superconducting applications such as detectors for astrophysics, high energy experiments, medicine imaging and so on.