Learning magnetization dynamics

Abstract

Deep neural networks are used to model the magnetization dynamics in magnetic thin film elements. The magnetic states of a thin film element can be represented in a low dimensional space. With convolutional autoencoders a compression ratio of 1024:1 was achieved. Time integration can be performed in the latent space with a second network which was trained by solutions of the Landau-Lifshitz-Gilbert equation. Thus the magnetic response to an external field can be computed quickly.

References in corpus (5)

• Fast and Accurate Deep Network Learning by Exponential Linear Units (ELUs)
• Deep Fluids: A Generative Network for Parameterized Fluid Simulations
• Fidimag -- a finite difference atomistic and micromagnetic simulation package
• Large Scale Finite-Element Simulation of Micromagnetic Thermal Noise
• Learning time-stepping by nonlinear dimensionality reduction to predict magnetization dynamics

Cited by in corpus (10)

• Magnetostatics and micromagnetics with physics informed neural networks
• Conditional physics informed neural networks
• Forecasting the outcome of spintronic experiments with Neural Ordinary Differential Equations
• Computational Micromagnetics based on Normal Modes: bridging the gap between macrospin and full spatial discretization
• Physics-informed machine learning and stray field computation with application to micromagnetic energy minimization
• Machine learning methods for the prediction of micromagnetic magnetization dynamics
• Learning time-stepping by nonlinear dimensionality reduction to predict magnetization dynamics
• Prediction of magnetization dynamics in a reduced dimensional feature space setting utilizing a low-rank kernel method
• Recurrent network classifier for ultrafast skyrmion dynamics
• Modern triad for magnetic material science: geometric shape, electronic bands and spin textures