论文标题
使用光学神经网络的光子波导中的引导模式的设计和分析
Design and analysis of guided modes in photonic waveguides using optical neural network
论文作者
论文摘要
我们使用光学神经网络提出了一种深度学习方法，以预测硅（SI）通道波导中的基本模态索引$ n _ {\ rm {eff}} $。我们使用三个输入，例如两个几何参数和一个材料属性，并预测用于横向电气和横向磁性极化的$ n _ {\ rm {eff}} $。从麦克斯韦方程中的精确模式解决方案的最小数字（即$ 3^3 $或$ 4^3 $）的情况下，我们可以发现对应于$ 10^3 $数值模拟的解决方案。请注意，这消耗了最低的计算资源。确切的平均平方错误和预测结果为$ <10^{ - 5} $。此外，我们的参数范围与当前的光刻图和互补的金属氧化物 - 氧化型（CMOS）制造技术兼容。我们还显示了不同传输功能和神经网络布局对模型性能的影响。我们的方法提出了一个独特的优势，可以在最小可能的数值模拟中发现任何光子波导中的引导模式。
We present a deep learning approach using an optical neural network to predict the fundamental modal indices $n_{\rm{eff}}$ in a silicon (Si) channel waveguide. We use three inputs, e.g., two geometric parameters and one material property, and predict the $n_{\rm{eff}}$ for the transverse electric and transverse magnetic polarizations. With the least number (i.e., $3^3$ or $4^3$) of exact mode solutions from Maxwell's equations, we can uncover the solutions which correspond to $10^3$ numerical simulations. Note that this consumes the lowest amount of computational resources. The mean squared errors of the exact and the predicted results are $<10^{-5}$. Moreover, our parameters' ranges are compatible with current photolithography and complementary metal-oxide-semiconductor (CMOS) fabrication technology. We also show the impacts of different transfer functions and neural network layouts on the model's performance. Our approach presents a unique advantage to uncover the guided modes in any photonic waveguides within the least possible numerical simulations.
