Forecasting the outcome of spintronic experiments with Neural Ordinary Differential Equations

Abstract

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 (ODEs) to the constraints of spintronics: few measured outputs, multiple inputs and internal parameters. We demonstrate with Spin-Neural ODEs 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 Spin-Neural ODEs on five milliseconds of their measured response to different excitations. Spin-Neural ODE is 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. Spin-Neural ODE can also be generalized to other electronic devices involving dynamics.

arXiv comment16 pages, 4 figures

References in corpus (24)

• The design and verification of Mumax3
• Advances in the Physics of Magnetic Skyrmions and Perspective for Technology
• Recent Advances in Physical Reservoir Computing: A Review
• Quantum-Chemical Insights from Deep Tensor Neural Networks
• Machine Learning of Accurate Energy-Conserving Molecular Force Fields
• Magnetic skyrmion artificial synapse for neuromorphic computing
• Vowel recognition with four coupled spin-torque nano-oscillators
• Thermal skyrmion diffusion applied in probabilistic computing
• Magnetic skyrmion-based synaptic devices
• Nanoscale neural network using non-linear spin-wave interference
• Reservoir Computing with Random Skyrmion Textures
• Micromagnetics and spintronics: Models and numerical methods
• Learning Molecular Dynamics with Simple Language Model built upon Long Short-Term Memory Neural Network
• Modeling System Dynamics with Physics-Informed Neural Networks Based on Lagrangian Mechanics
• Spatio-Temporal Neural Networks for Space-Time Series Forecasting and Relations Discovery
• Parameterized Neural Ordinary Differential Equations: Applications to Computational Physics Problems
• Exploring neural network training strategies to determine phase transitions in frustrated magnetic models
• Extracting local switching fields in permanent magnets using machine learning
• Radio-Frequency Multiply-And-Accumulate Operations with Spintronic Synapses
• Learning magnetization dynamics
• Machine learning methods for the prediction of micromagnetic magnetization dynamics
• Prediction of magnetization dynamics in a reduced dimensional feature space setting utilizing a low-rank kernel method
• Magnetic skyrmion spectrum under voltage excitation and its linear modulation
• Deep Neural Networks to Recover Unknown Physical Parameters from Oscillating Time Series

Cited by in corpus (6)

• Pattern recognition with neuromorphic computing using magnetic-field induced dynamics of skyrmions
• A perspective on physical reservoir computing with nanomagnetic devices
• Feedback-driven quantum reservoir computing for time-series analysis
• Skyrmion based energy efficient straintronic physical reservoir computing
• Practical Few-Atom Quantum Reservoir Computing
• Forecasting with an N-dimensional Langevin Equation and a Neural-Ordinary Differential Equation