Magnetic Hamiltonian parameter estimation using deep learning techniques

Kwon, Hee Young; Yoon, Hanna; Lee, C.; Chen, G.; Liu, Kai; Schmid, Andreas K.; Wu, Y. Z.; Choi, Jun Woo; Won, C.

doi:10.1126/sciadv.abb0872

Cited by 31 publications

(31 citation statements)

References 41 publications

(56 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The present method can be helpful for a broader field, like, there is a potential application in topological-dependent stochastic process [52], in which the topological charge could be extracted by the deep CNNs in a similar manner. Moreover, the transfer learning could also help us to understand the stochastic process through introducing the well-trained deep CNNs into real physical observations [53].…”

Section: Discussionmentioning

confidence: 99%

Deep learning stochastic processes with QCD phase transition

Jiang,

Wang,

Zhou

2021

Preprint

View full text Add to dashboard Cite

Section: Discussionmentioning

confidence: 99%

Deep learning stochastic processes with QCD phase transition

Jiang,

Wang,

Zhou

2021

Preprint

View full text Add to dashboard Cite

“…In recent years, machine learning has been increasingly used in physics, for example, for discovering new materials and learning physical dynamics from time-series data. 20 – 30 . In the field of nanomagnetism and micromagnetics, deep neural networks are used to extract microstructural features in magnetic thin film elements 31 – 34 , and to explore materials with ease 35 .…”

Section: Introductionmentioning

confidence: 99%

Forecasting the outcome of spintronic experiments with Neural Ordinary Differential Equations

et al. 2022

View full text Add to dashboard Cite

Deep learning has an increasing impact to assist research, allowing, for example, the discovery of novel materials. Until now, however, these artificial intelligence techniques have fallen short of discovering the full differential equation of an experimental physical system. Here we show that a dynamical neural network, trained on a minimal amount of data, can predict the behavior of spintronic devices with high accuracy and an extremely efficient simulation time, compared to the micromagnetic simulations that are usually employed to model them. For this purpose, we re-frame the formalism of Neural Ordinary Differential Equations to the constraints of spintronics: few measured outputs, multiple inputs and internal parameters. We demonstrate with Neural Ordinary Differential Equations an acceleration factor over 200 compared to micromagnetic simulations for a complex problem – the simulation of a reservoir computer made of magnetic skyrmions (20 minutes compared to three days). In a second realization, we show that we can predict the noisy response of experimental spintronic nano-oscillators to varying inputs after training Neural Ordinary Differential Equations on five milliseconds of their measured response to a different set of inputs. Neural Ordinary Differential Equations can therefore constitute a disruptive tool for developing spintronic applications in complement to micromagnetic simulations, which are time-consuming and cannot fit experiments when noise or imperfections are present. Our approach can also be generalized to other electronic devices involving dynamics.

show abstract

“…25 The advanced CNN methods showed effectiveness and accuracy in different research domains. However, these methods generally require a large data set 26 to properly train and test the model, which might stand in the way of directly using these methods in analyzing regular experimental data.…”

Section: ■ Introductionmentioning

confidence: 99%

Understanding the Magnetic Microstructure through Experiments and Machine Learning Algorithms

Talapatra

Gajera

et al. 2022

ACS Appl. Mater. Interfaces

View full text Add to dashboard Cite

Advanced machine learning techniques have unfurled their applications in various interdisciplinary areas of research and development. This paper highlights the use of image regression algorithms based on advanced neural networks to understand the magnetic properties directly from the magnetic microstructure. In this study, Co/Pd multilayers have been chosen as a reference material system that displays maze-like magnetic domains in pristine conditions. Irradiation of Ar+ ions with two different energies (50 and 100 keV) at various fluences was used as an external perturbation to investigate the modification of magnetic and structural properties from a state of perpendicular magnetic anisotropy to the vicinity of the spin reorientation transition. Magnetic force microscopy revealed domain fragmentation with a smaller periodicity and weaker magnetic contrast up to the fluence of 1014 ions/cm2. Further increases in the ion fluence result in the formation of feather-like domains with a variation in local magnetization distribution. The experimental results were complemented with micromagnetic simulations, where the variations of effective magnetic anisotropy and exchange constant result in qualitatively similar changes in magnetic domains, as observed experimentally. Importantly, a set of 960 simulated domain images was generated to train, validate, and test the convolutional neural network (CNN) that predicts the magnetic properties directly from the domain images with a high level of accuracy (maximum 93.9%). Our work has immense importance in promoting the applications of image regression methods through the CNN in understanding integral magnetic properties obtained from the microscopic features subject to change under external perturbations.

show abstract

Magnetic Hamiltonian parameter estimation using deep learning techniques

Cited by 31 publications

References 41 publications

Deep learning stochastic processes with QCD phase transition

Deep learning stochastic processes with QCD phase transition

Forecasting the outcome of spintronic experiments with Neural Ordinary Differential Equations

Understanding the Magnetic Microstructure through Experiments and Machine Learning Algorithms

Contact Info

Product

Resources

About