Wang Xiuzhu, Xiao Zhihua, Wu Xuezhao, Zhou Yan, Shao Qiming
Department of Electronic and Computer Engineering, The Hong Kong University of Science and Technology, Hong Kong Special Administrative Region of China, People's Republic of China.
AI Chip Center for Emerging Smart Systems, InnoHK Centers, Hong Kong Science Park, Hong Kong Special Administrative Region of China, People's Republic of China.
Nanotechnology. 2025 Jun 18;36(26). doi: 10.1088/1361-6528/ade242.
The topologically stabilized quasi-particle skyrmion is one of the most significant spin structures. Its unique physical properties-such as stability, nanoscale size, and efficient manipulability-make it a promising candidate for applications in high-density data storage, low-power in-memory computing, and neuromorphic devices. Skyrmions are typically generated from ferromagnetic states using field-tuning or current-tuning methods, which involve applying magnetic fields with varying gradients and sequences or spin-current pulses with specific amplitudes and polarizations. However, the complexity of these applied field or current sequences during skyrmion generation often leads to numerous intermediate phases, making the process repetitive and heavily reliant on trial and error. To address this challenge, we propose a phase-control method based on reinforcement learning (RL) to optimize field control for skyrmion generation. The RL framework incorporates a carefully designed reward system, guided by physical insights, that considers the topological number and feature states while encouraging diverse field-tuning modes. Training results demonstrate that the network can progressively learn and optimize the field sequences required for skyrmion generation. Once trained, the network is capable of autonomously and reliably generating skyrmions, significantly reducing the need for manual intervention and trial-and-error adjustments. This approach has broader potential applications, including the generation of other spintronic structures such as chiral domain walls and magnetic vortices. It represents a valuable contribution to AI-driven spintronic simulations, bridging the gap between computational models and experimental implementations, and advancing the development of next-generation spintronic technologies.
拓扑稳定的准粒子斯格明子是最重要的自旋结构之一。其独特的物理性质，如稳定性、纳米级尺寸和高效的可操控性，使其成为高密度数据存储、低功耗内存计算和神经形态器件应用的有前途的候选者。斯格明子通常通过场调谐或电流调谐方法从铁磁态产生，这涉及施加具有不同梯度和序列的磁场或具有特定幅度和极化的自旋电流脉冲。然而，在斯格明子产生过程中这些应用的场或电流序列的复杂性常常导致许多中间相，使得该过程重复且严重依赖试错法。为应对这一挑战，我们提出一种基于强化学习（RL）的相位控制方法，以优化斯格明子产生的场控制。RL框架包含一个经过精心设计的奖励系统，该系统由物理见解指导，在鼓励多种场调谐模式的同时考虑拓扑数和特征状态。训练结果表明，该网络可以逐步学习和优化斯格明子产生所需的场序列。一旦训练完成，该网络能够自主且可靠地产生斯格明子，显著减少人工干预和试错调整的需求。这种方法具有更广泛的潜在应用，包括产生其他自旋电子结构，如手性畴壁和磁涡旋。它为人工智能驱动的自旋电子模拟做出了有价值的贡献，弥合了计算模型与实验实现之间的差距，并推动了下一代自旋电子技术的发展。
