Beneke Grischa, Winkler Thomas Brian, Raab Klaus, Brems Maarten A, Kammerbauer Fabian, Gerhards Pascal, Knobloch Klaus, Krishnia Sachin, Mentink Johan H, Kläui Mathias
Institut für Physik, Johannes Gutenberg-Universität Mainz, Mainz, 55099, Germany.
Infineon Technologies Dresden, Dresden, 01099, Germany.
Nat Commun. 2024 Sep 16;15(1):8103. doi: 10.1038/s41467-024-52345-y.
Physical reservoir computing leverages the dynamical properties of complex physical systems to process information efficiently, significantly reducing training efforts and energy consumption. Magnetic skyrmions, topological spin textures, are promising candidates for reservoir computing systems due to their enhanced stability, non-linear interactions and low-power manipulation. Traditional spin-based reservoir computing has been limited to quasi-static detection or real-world data must be rescaled to the intrinsic timescale of the reservoir. We address this challenge by time-multiplexed skyrmion reservoir computing, that allows for aligning the reservoir's intrinsic timescales to real-world temporal patterns. Using millisecond-scale hand gestures recorded with Range-Doppler radar, we feed voltage excitations directly into our device and detect the skyrmion trajectory evolution. This method scales down to the nanometer level and demonstrates competitive or superior performance compared to energy-intensive software-based neural networks. Our hardware approach's key advantage is its ability to integrate sensor data in real-time without temporal rescaling, enabling numerous applications.
物理储层计算利用复杂物理系统的动力学特性来高效处理信息，显著减少训练工作量和能耗。磁斯格明子，即拓扑自旋纹理，因其增强的稳定性、非线性相互作用和低功耗操控，是储层计算系统的有前途的候选者。传统的基于自旋的储层计算一直局限于准静态检测，或者必须将现实世界的数据重新缩放到储层的固有时间尺度。我们通过时分复用斯格明子储层计算来应对这一挑战，这种方法允许将储层的固有时间尺度与现实世界的时间模式对齐。使用距离-多普勒雷达记录的毫秒级手势，我们将电压激励直接输入到我们的设备中，并检测斯格明子轨迹的演变。这种方法可以缩小到纳米级别，并且与能耗高的基于软件的神经网络相比，展示出具有竞争力或更优的性能。我们硬件方法的关键优势在于它能够实时集成传感器数据而无需时间重新缩放，从而实现众多应用。
