logo
ResearchBunny Logo
Forecasting the outcome of spintronic experiments with Neural Ordinary Differential Equations

Engineering and Technology

Forecasting the outcome of spintronic experiments with Neural Ordinary Differential Equations

X. Chen, F. A. Araujo, et al.

Discover the groundbreaking research by Xing Chen, Flavio Abreu Araujo, and their team, showcasing the use of Neural Ordinary Differential Equations (NODEs) to revolutionize spintronic device simulations. Their innovative approach offers over 200 times acceleration compared to traditional methods, making it a game-changer in the field.

00:00
00:00
Playback language: English
Abstract
This paper demonstrates the use of Neural Ordinary Differential Equations (NODEs) to predict the behavior of spintronic devices with high accuracy and significantly faster simulation times compared to traditional micromagnetic simulations. The authors modify the NODE formalism to address the challenges of limited measured outputs and multiple inputs in spintronics, achieving an acceleration factor over 200 in a complex skyrmion-based reservoir computer simulation. The approach is further validated by accurately predicting the noisy response of experimental spintronic nano-oscillators, highlighting its potential as a disruptive tool for spintronic applications and other dynamic electronic devices.
Publisher
Nature Communications
Published On
Feb 23, 2022
Authors
Xing Chen, Flavio Abreu Araujo, Mathieu Riou, Jacob Torrejon, Dafiné Ravelosona, Wang Kang, Weisheng Zhao, Julie Grollier, Damien Querlioz
Tags
Neural Ordinary Differential Equations
spintronics
simulation acceleration
spintronic devices
skyrmion
nano-oscillators
dynamic electronic devices

Related Publications

Explore these studies to deepen your understanding of the subject.

Developing a BOPPPS (Bridge-in, Objectives, Pre-assessment, Participatory Learning, Post-assessment and Summary) model combined with the OBE (Outcome Based Education) concept to improve the teaching outcomes of higher education
Education

Developing a BOPPPS (Bridge-in, Objectives, Pre-assessment, Participatory Learning, Post-assessment and Summary) model combined with the OBE (Outcome Based Education) concept to improve the teaching outcomes of higher education

Z. Xu, L. Ge, et al.

Critical outcomes to be included in the Core Outcome Set for nutritional intervention studies in older adults with malnutrition or at risk of malnutrition: a modified Delphi Study
Medicine and Health

Critical outcomes to be included in the Core Outcome Set for nutritional intervention studies in older adults with malnutrition or at risk of malnutrition: a modified Delphi Study

N. Mendonça, C. Avgerinou, et al.

Automatically discovering ordinary differential equations from data with sparse regression
Engineering and Technology

Automatically discovering ordinary differential equations from data with sparse regression

K. Egan, W. Li, et al.

Early forecasting of tsunami inundation from tsunami and geodetic observation data with convolutional neural networks
Earth Sciences

Early forecasting of tsunami inundation from tsunami and geodetic observation data with convolutional neural networks

F. Makinoshima, Y. Oishi, et al.

Listen, Learn & Level Up
Over 10,000 hours of research content in 25+ fields, available in 12+ languages.
No more digging through PDFs, just hit play and absorb the world's latest research in your language, on your time.
listen to research audio papers with researchbunny