Theoretical basis of SQUID-based artificial neurons
JApplPhys_124_152106.pdf.pdf 251 KB
The physical basis of an artificial neuron is studied using a model that is based on the stochastic transition between two states in a double well potential. It is shown that the stochastic transition model generates an energy-defined sigmoid function acting as an activation (or transfer) function in neurons. The model is also applied to circuit neurons using superconducting quantum interference devices in artificial neural networks.
PACS numbers: 87.19.ll, 85.25.Dq, 07.05.Mh.
This work is supported in part by MEXT (17K05579).
Journal of Applied Physics
|date of issued||
This document is the Accepted Manuscript version of a Published Work that appeared in final form in Journal of Applied Physics, copyright © AIP Publishing after peer review and technical editing by the publisher. To access the final edited and published work see https://doi.org/10.1063/1.5037718.
This is not the published version. Please cite only the published version. この論文は出版社版でありません。引用の際には出版社版をご確認、ご利用ください。
Graduate School of Integrated Arts and Sciences