[论文解读] Diffractive Interconnects: All-Optical Permutation Operation Using Diffractive Networks

Deniz Mengü, Yifan Zhao+3 more|arXiv (Cornell University)|Jun 21, 2022

Optical Network Technologies参考文献 87被引用 22

一句话总结

本论文提出一种通过深度学习训练的衍射光学网络，可在大规模场景下实现全光排列操作，从而实现被动、低功耗且高速的数十万路输入-输出通道互连。该工作首次实验演示了太赫兹频段的衍射排列网络，利用3D打印的透射层实现625路互连，且训练后对物理错位和制造误差具有鲁棒性。

ABSTRACT

Permutation matrices form an important computational building block frequently used in various fields including e.g., communications, information security and data processing. Optical implementation of permutation operators with relatively large number of input-output interconnections based on power-efficient, fast, and compact platforms is highly desirable. Here, we present diffractive optical networks engineered through deep learning to all-optically perform permutation operations that can scale to hundreds of thousands of interconnections between an input and an output field-of-view using passive transmissive layers that are individually structured at the wavelength scale. Our findings indicate that the capacity of the diffractive optical network in approximating a given permutation operation increases proportional to the number of diffractive layers and trainable transmission elements in the system. Such deeper diffractive network designs can pose practical challenges in terms of physical alignment and output diffraction efficiency of the system. We addressed these challenges by designing misalignment tolerant diffractive designs that can all-optically perform arbitrarily-selected permutation operations, and experimentally demonstrated, for the first time, a diffractive permutation network that operates at THz part of the spectrum. Diffractive permutation networks might find various applications in e.g., security, image encryption and data processing, along with telecommunications; especially with the carrier frequencies in wireless communications approaching THz-bands, the presented diffractive permutation networks can potentially serve as channel routing and interconnection panels in wireless networks.

研究动机与目标

• 开发一种可扩展的全光方法，利用无源衍射光学网络实现大规模排列操作。
• 解决深度衍射光学系统中物理对准和衍射效率的实际挑战。
• 通过深度学习设计对错位容忍的衍射网络，使其对横向、轴向和旋转误差具有鲁棒性。
• 通过3D打印的衍射层实验验证首个太赫兹频段衍射排列网络。
• 推动太赫兹通信、光互连和安全数据处理等应用的发展。

提出的方法

• 利用深度学习训练衍射光学网络，以在多层透射介质上设计相位和振幅调制。
• 使用随机梯度下降和误差反向传播算法，在波长尺度上优化传输元件。
• 在训练过程中将物理错位（横向、轴向、旋转）建模为随机变量，以增强鲁棒性。
• 通过在训练中引入材料厚度的统计波动，使网络对制造误差具有韧性。
• 采用前向模型，逐个激活输入像素以记录输出强度分布，从而形成排列矩阵的列。
• 应用缩放因子σP以考虑光学损耗，并使用PSNR和SSIM指标计算性能。

实验结果

研究问题

• RQ1 通过深度学习训练的衍射光学网络能否以高精度和可扩展性实现大规模排列操作？
• RQ2 衍射层数量和可训练元件数量如何影响网络对给定排列的逼近能力？
• RQ3 通过训练，衍射网络在多大程度上可对物理错位和制造缺陷实现鲁棒性？
• RQ4 能否在太赫兹频段实验演示具有高互连密度的衍射排列网络？
• RQ5 在真实物理误差条件下，此类网络的PSNR和SSIM性能如何？

主要发现

• 在实验演示中，衍射网络对25×25排列矩阵实现了34.2 dB的PSNR和0.98的SSIM。
• 该网络仅通过一次全光传输即成功实现了625路互连（25×25），工作于太赫兹频段，使用3D打印的衍射层。
• 性能随衍射层数和可训练传输元件数量的增加而提升，表明可扩展至数十万路互连。
• 经训练的疫苗化衍射网络（v-D2NN）在模拟错位条件下保持高精度，其中∆x = ∆y = 0.67λv，∆z = 24λv，∆θ = 4°，v = 0.5。
• 网络被训练以容忍衍射神经元间材料厚度±0.0415λ的变化，证明对制造误差具有鲁棒性。
• 使用GTX 1080 Ti GPU训练包含5层、每层40,000个神经元的网络，耗时约4天（5个训练周期），证实了训练流程的可行性。