Chen Xing, Araujo Flavio Abreu, Riou Mathieu, Torrejon Jacob, Ravelosona Dafiné, Kang Wang, Zhao Weisheng, Grollier Julie, Querlioz Damien
Fert Beijing Institute, MIIT Key Laboratory of Spintronics, School of Integrated Circuit Science and Engineering, Beihang University, 100191, Beijing, China.
Université Paris-Saclay, CNRS, Centre de Nanosciences et de Nanotechnologies, Palaiseau, France.
Nat Commun. 2022 Feb 23;13(1):1016. doi: 10.1038/s41467-022-28571-7.
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.
深度学习在辅助研究方面的影响力日益增强，例如有助于发现新型材料。然而，到目前为止，这些人工智能技术尚未能发现实验物理系统的完整微分方程。在此我们表明，与通常用于对自旋电子器件进行建模的微磁模拟相比，在少量数据上训练的动态神经网络能够以高精度和极高效的模拟时间预测自旋电子器件的行为。为此，我们将神经常微分方程的形式体系重新构建以适应自旋电子学的约束条件：少量测量输出、多个输入和内部参数。对于一个复杂问题——由磁斯格明子构成的储层计算机的模拟（微磁模拟需要三天，而神经常微分方程模拟只需20分钟），我们通过神经常微分方程证明其加速因子超过200。在第二个实例中，我们表明，在对实验自旋电子纳米振荡器对不同输入的五毫秒测量响应进行神经常微分方程训练后，我们能够预测其对变化输入的噪声响应。因此，神经常微分方程可以成为开发自旋电子学应用的一种突破性工具，以补充微磁模拟，微磁模拟耗时且在存在噪声或缺陷时无法拟合实验。我们的方法还可以推广到涉及动力学的其他电子器件。
