Machine Learning Magnetic Parameters from Spin Configurations
Dingchen Wang,Songrui Wei,Anran Yuan,Fanghua Tian,Kaiyan Cao,Qizhong Zhao,Yin Zhang,Chao Zhou,Xiaoping Song,Dezhen Xue,Sen Yang +10 more
TL;DR: In this paper, a machine learning-based approach for estimating Hamiltonian parameters from high-resolution images based on a small amount of simulated images is proposed. But the approach is limited to a single unexplored experimental image and cannot predict the corresponding materials properties.
read more
Abstract: Hamiltonian parameters estimation is crucial in condensed matter physics, but is time- and cost-consuming. High-resolution images provide detailed information of underlying physics, but extracting Hamiltonian parameters from them is difficult due to the huge Hilbert space. Here, a protocol for Hamiltonian parameters estimation from images based on a machine learning (ML) architecture is provided. It consists in learning a mapping between spin configurations and Hamiltonian parameters from a small amount of simulated images, applying the trained ML model to a single unexplored experimental image to estimate its key parameters, and predicting the corresponding materials properties by a physical model. The efficiency of the approach is demonstrated by reproducing the same spin configuration as the experimental one and predicting the coercive field, the saturation field, and even the volume of the experiment specimen accurately. The proposed approach paves a way to achieve a stable and efficient parameters estimation.
read more
Chat with Paper
AI Agents for this Paper
Find similar papers on Google Scholar, PubMed and Arxiv
Write a critical review of this paper
Analyze citations of this paper to find unaddressed research gaps
Citations
•Journal Article
Learning phase transitions by confusion
TL;DR: This work proposes a neural-network approach to finding phase transitions, based on the performance of a neural network after it is trained with data that are deliberately labelled incorrectly, and paves the way to the development of a generic tool for identifying unexplored phase transitions.
•Posted Content
A machine learning approach to Bayesian parameter estimation
TL;DR: This theoretical study forms parameter estimation as a classification task and uses artificial neural networks to efficiently perform Bayesian estimation, showing that the network’s posterior distribution is centered at the true (unknown) value of the parameter within an uncertainty given by the inverse Fisher information, representing the ultimate sensitivity limit for the given apparatus.
67
On-the-fly interpretable machine learning for rapid discovery of two-dimensional ferromagnets with high Curie temperature
TL;DR: In this article , an adaptive ML framework was developed to search the chemical space containing over 2 × 10 5 candidates, and an adaptive representation set, coupling with magnetism, crystal field theory, and atomic environments, was built.
55
•Journal Article
Extended skyrmion phase in epitaxial FeGe(111) thin films
TL;DR: In this article, the authors extended the topological Hall effect on the Skyrmion state in epitaxial B20 FeGe(111) thin films to cover all temperatures up to the Curie temperature T(C)≈271 K and over a wide magnetic field range.
Learning Many-Body Hamiltonians with Heisenberg-Limited Scaling
16 May 2023
TL;DR: In this article , the authors proposed a quantum-enhanced divide-and-conquer approach to learn an interacting N-qubit local Hamiltonian in O(n − 1 ) time.
References
Real-space observation of a two-dimensional skyrmion crystal
X. Z. Yu,Yoshinori Onose,Naoya Kanazawa,Jin-Hong Park,Jung Hoon Han,Yoshio Matsui,Naoto Nagaosa,Yoshinori Tokura +7 more
TL;DR: Real-space imaging of a two-dimensional skyrmion lattice in a thin film of Fe0.5Co 0.5Si using Lorentz transmission electron microscopy reveals a controlled nanometre-scale spin topology, which may be useful in observing unconventional magneto-transport effects.
3.6K
The design and verification of MuMax3
Arne Vansteenkiste,Jonathan Leliaert,Mykola Dvornik,Mathias Helsen,Felipe Garcia-Sanchez,Bartel Van Waeyenberge +5 more
TL;DR: The design, verification and performance of MUMAX3, an open-source GPU-accelerated micromagnetic simulation program that solves the time- and space dependent magnetization evolution in nano- to micro scale magnets using a finite-difference discretization is reported on.
3.1K
The design and verification of Mumax3
Arne Vansteenkiste,Jonathan Leliaert,Mykola Dvornik,Felipe Garcia-Sanchez,Bartel Van Waeyenberge +4 more
TL;DR: In this paper, the authors report on the design, verification and performance of mumax3, an open-source GPU-accelerated micromagnetic simulation program that solves the time and space dependent magnetization evolution in nano-to micro-scale magnets using a finite-difference discretization.
2.6K
Solving the quantum many-body problem with artificial neural networks
TL;DR: In this paper, a variational representation of quantum states based on artificial neural networks with a variable number of hidden neurons is introduced. But this model is not suitable for the many-body problem in quantum physics.
2K
Nucleation, stability and current-induced motion of isolated magnetic skyrmions in nanostructures
TL;DR: It is demonstrated by numerical investigations that an isolated skyrmion can be a stable configuration in a nanostructure, can be locally nucleated by injection of spin-polarized current, and can be displaced by current-induced spin torques, even in the presence of large defects.
1.9K