[论文解读] Response to Comment on "All-optical machine learning using diffractive deep neural networks"

Deniz Mengü, Yi Luo+4 more|arXiv (Cornell University)|Oct 10, 2018

Neural Networks and Reservoir Computing被引用 6

一句话总结

本文回应了针对衍射深度神经网络（D2NNs）线性和无源性的批评，重申其深度和光学非线性特性使其在全光机器学习中表现更优。本文证明，增加衍射层的数量可提升分类准确率、信号对比度和衍射效率，从而证实D2NNs在全光机器学习中具备深度优势。

ABSTRACT

In their Comment, Wei et al. (arXiv:1809.08360v1 [cs.LG]) claim that our original interpretation of Diffractive Deep Neural Networks (D2NN) represent a mischaracterization of the system due to linearity and passivity. In this Response, we detail how this mischaracterization claim is unwarranted and oblivious to several sections detailed in our original manuscript (Science, DOI: 10.1126/science.aat8084) that specifically introduced and discussed optical nonlinearities and reconfigurability of D2NNs, as part of our proposed framework to enhance its performance. To further refute the mischaracterization claim of Wei et al., we, once again, demonstrate the depth feature of optical D2NNs by showing that multiple diffractive layers operating collectively within a D2NN present additional degrees-of-freedom compared to a single diffractive layer to achieve better classification accuracy, as well as improved output signal contrast and diffraction efficiency as the number of diffractive layers increase, showing the deepness of a D2NN, and its inherent depth advantage for improved performance. In summary, the Comment by Wei et al. does not provide an amendment to the original teachings of our original manuscript, and all of our results, core conclusions and methodology of research reported in Science (DOI: 10.1126/science.aat8084) remain entirely valid.

研究动机与目标

• 反驳关于衍射深度神经网络（D2NNs）因线性和无源性而存在根本性限制的论断。
• 重申2018年发表于《科学》杂志的原始D2NN框架的有效性，包括其对光学非线性和可重构性的应用。
• 证明增加衍射层的数量可提升分类准确率、输出信号对比度和衍射效率等性能指标。
• 确立D2NNs的深度相较于单层系统具备固有优势，从而验证原始研究的核心方法论。

提出的方法

• 重申原始D2NN框架中明确包含光学非线性和可重构性，如《科学》论文中所详述。
• 分析多层衍射结构的集体行为，表明其相较于单层配置具有更高的自由度。
• 证明随着衍射层数量的增加，性能指标（包括分类准确率、输出信号对比度和衍射效率）均得到提升。
• 通过理论与实证分析表明，系统的深度可实现对光传播更优的优化，以适应机器学习任务。
• 强调系统性能不受线性或无源性限制，因其框架支持非线性光学响应与动态可重构性。
• 重申《科学》论文中原始的实验与理论结果依然有效，且未被该批评所动摇。

实验结果

研究问题

• RQ1 能否通过增加衍射神经网络的深度来提升全光机器学习系统的性能？
• RQ2 在D2NNs中引入光学非线性和可重构性是否能克服线性和无源性带来的限制？
• RQ3 相较于单层系统，多层衍射结构如何协同提升分类准确率、信号对比度和衍射效率？
• RQ4 D2NNs的深度是否是光学机器学习的根本优势，还是仅属结构上的副产品？
• RQ5 魏等人提出的批评是否准确反映了《科学》论文中原始D2NN框架的实际情况？

主要发现

• 原始手稿中已明确阐述D2NN框架中包含光学非线性和可重构性，反驳了存在疏漏的论断。
• 增加衍射层数量可显著提升分类准确率、输出信号对比度和衍射效率。
• 多层衍射结构提供了额外的自由度，使光传播在机器学习任务中可实现更优优化。
• D2NN架构的深度相较于浅层配置具备固有性能优势。
• 魏等人的批评并未推翻原始发现，且《科学》论文中的所有核心结论依然有效。
• 本回应确认D2NN框架不受线性或无源性限制，因其支持非线性和可重构的光学响应。