Superconducting base elements for brain-like artificial neura network

Abstract

Increasing energy consumption of computers with von-Neumann architecture rose the necessity of energy efficiency and the radically reduction of the power consumption as a crucial parameter constraining the advance of supercomputers. The promising solution is development of the non-von Neumann computers with brain-like architecture – the Artificial Neural Networks (ANN) based on superconducting elements with two main parts: nonlinear switch similar to the neuron, and linear connecting elements similar to synapse. We present results of design and investigation of artificial neurons, based on superconducting spin valves, and superconducting synapses, based on layered hybrid nanostructures superconductor-ferromagnet.