Tunable superconducting neurons for networks based on radial basis functions

The hardware implementation of signal microprocessors based on superconducting technologies seems relevant for a number of niche tasks where performance and energy efficiency are critically important. In this paper, we consider the basic elements for superconducting neural networks on radial basis functions. We examine the static and dynamic activation functions of the proposed neuron. Special attention is paid to tuning the activation functions to a Gaussian form with relatively large amplitude. For the practical implementation of the required tunability, we proposed and investigated heterostructures designed for the implementation of adjustable inductors that consist of superconducting, ferromagnetic, and normal layers.

Automated summary

The paper explores the hardware implementation of signal microprocessors based on superconducting technologies for niche tasks requiring high performance and energy efficiency. It focuses on superconducting neural networks utilizing radial basis functions, examining static and dynamic activation functions of neurons as well as the design of adjustable inductors for practical implementation.