公开(公告)号：US20210365615A1

公开(公告)日：2021-11-25

申请号：US17072384

申请日：2020-10-16

Applicant: KOREA INSTITUTE OF SCIENCE AND TECHNOLOGY

Inventor： Hee Young Kwon ,  Jun Woo Choi

IPC: G06F30/27 ,  G06N3/04

Abstract: Disclosed is a magnetic parameter value estimation method using deep learning, the magnetic parameter value estimation method including creating a simulated magnetic domain image corresponding to a spin configuration of a two-dimensional magnetic system created through computer simulation, modeling a deep neural network using the simulated magnetic domain image, and estimating a magnetic parameter value of an observed magnetic domain image using the modeled deep neural network.

公开(公告)号：US11934754B2

公开(公告)日：2024-03-19

申请号：US17072384

申请日：2020-10-16

Applicant: KOREA INSTITUTE OF SCIENCE AND TECHNOLOGY

Inventor： Hee Young Kwon ,  Jun Woo Choi

IPC: G06F30/27 ,  G06N3/04 ,  G06N3/045 ,  G06N3/08 ,  G06N5/01 ,  G06N7/01 ,  G06N20/00 ,  H01F7/02 ,  G06F111/10

CPC classification number: G06F30/27 ,  G06N3/04 ,  G06N3/045 ,  G06N3/08 ,  G06N5/01 ,  G06N7/01 ,  G06N20/00 ,  H01F7/0294 ,  G06F2111/10

Abstract: Disclosed is a magnetic parameter value estimation method using deep learning, the magnetic parameter value estimation method including creating a simulated magnetic domain image corresponding to a spin configuration of a two-dimensional magnetic system created through computer simulation, modeling a deep neural network using the simulated magnetic domain image, and estimating a magnetic parameter value of an observed magnetic domain image using the modeled deep neural network.