标题： 具有角形GST调制的双微环谐振器：为神经形态光子学实现超快速非线性激活 显示英文标题

标题： Dual Micro-Ring Resonators with Angular GST Modulation: Enabling Ultra-Fast Nonlinear Activation for Neuromorphic Photonics

摘要： 光子技术正在成为神经形态计算的强大推动者，通过提供超快且能效高的神经功能。在本工作中，我们提出并展示了一种新颖的全光双微环谐振器架构，结合相变材料Ge2Sb2Te5 (GST) 来实现高精度的非线性激活函数（NLAFs）。我们的方法在环中引入了GST段的角度定位，实现了对光传输动态的精细控制。通过系统评估十六种不同的相位配置，我们确定了第一环中180度和第二环中90度的最佳GST放置位置，实现了仅0.47纳米的全宽半最大值（FWHM）的超窄带传输。这种双环结构提供了两个不同的共振波长，促进了增强的非线性调制和多级光信号处理，这与生物神经元行为非常相似。值得注意的是，该器件在4纳米光谱窗口内实现了0到0.85的高对比度传输，同时在显著降低的温度（100摄氏度）下运行，优于传统的基于GST的设计。此外，双环架构实现了以前单环结构无法实现的光谱选择性和开关对比度能力的独立优化。这些结果为可扩展、高速的神经形态光子系统开辟了一条有前景的路径，提供了实际片上神经处理所需的精度和开关速度。 显示英文摘要

摘要： Photonic technologies are emerging as powerful enablers for neuromorphic computing by delivering ultrafast and energy efficient neural functionalities. In this work, we propose and demonstrate a novel all-optical dual micro ring resonator architecture incorporating the phase change material Ge2Sb2Te5 (GST) to implement highly precise nonlinear activation functions (NLAFs). Our approach introduces angular positioning of GST segments within the rings, enabling fine-grained control over optical transmission dynamics. Through a systematic evaluation of sixteen distinct phase configurations, we identify an optimal GST placement 180 deg in the first ring and 90 deg in the second that achieves ultra narrowband transmission with a full width at half maximum (FWHM) of just 0.47 nm. This dual ring configuration provides two distinct resonant wavelengths, facilitating enhanced nonlinear modulation and multi level optical signal processing that closely mimics biological neuron behavior. Notably, the device achieves high contrast transmission, 0 to 0.85, across a 4 nm spectral window while operating at significantly reduced temperatures (100 deg C), outperforming traditional GST based designs. Furthermore, the dual-ring architecture enables independent optimization of spectral selectivity and switching contrast capabilities previously unattainable with single ring structures. These results establish a promising pathway toward scalable, high speed neuromorphic photonic systems, offering both the precision and switching speed required for practical on chip neural processing.