arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2008.00398physics.opticsphysics.app-ph
收藏

利用光学神经网络设计和分析光子波导导模

Design and analysis of guided modes in photonic waveguides using optical neural network

Nusrat Jahan Anika, Md Borhan Mia

摘要:

我们提出了一种深度学习方法,使用光学神经网络来预测硅(Si)通道波导中的基本模式指数$n_{\rm{eff}}$。我们使用三个输入,例如,两个几何参数和一个材料性质,并预测了横向电场和横向磁场极化的$n_{\rm{eff}}$。以最少的数量(即,$3^3$或$4^3$)的精确模式解,我们可以揭示对应于$10^3$数值模拟的解决方案。请注意,这消耗的计算资源量最低。精确结果和预测结果的均方误差为$<10^{-5}$。此外,我们的参数范围与当前的光刻和互补金属氧化物半导体(CMOS)制造技术兼容。我们还展示了不同的传递函数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,揭示任何光子波导中的导模在尽可能少的数值模拟。

英文摘要:

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.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑