发表机构
University of California, Los Angeles（加州大学洛杉矶分校）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
本文提出一种波长复用的编码-解码衍射处理器，利用多波长照明在单层架构中实现大量非线性函数，无需级联或增加自由度，并通过数值模拟和实验验证了其可扩展性。
AI 中文摘要
衍射光学处理器通过利用工程化波传播来变换光场，为高通量、低延迟的模拟计算提供了一个有前景的平台。然而，在光学硬件中实现非线性映射仍然具有挑战性。在此，我们引入了一种波长复用的编码-解码（E+D）衍射处理器，该处理器利用多个照明波长来增强紧凑型单层衍射架构的非线性函数逼近能力，而无需级联多个衍射层或增加可训练自由度。在顺序波长扫描下，每个波长-探测器通道在衍射处理器的输出端实现一个不同的非线性函数。使用100个波长通道和衍射处理器输出端的10,000个空间探测器区域的数值模拟，展示了通过波长复用实现一百万个不同非线性函数的实现。我们还演示了一种同时多波长照明配置，其中E+D衍射处理器同时执行波分复用和非线性函数逼近。该多波长照明配置通过光学实现64个不同的非线性函数，在495至635纳米的八个波长同时照明下进行了实验验证。通过数值模拟和可见光实验演示，我们的结果表明，这种波长复用的非线性函数逼近框架为紧凑、高容量的衍射处理器提供了一条可扩展的路径，用于大规模模拟光学计算和光学信息处理。
英文摘要
Diffractive optical processors provide a promising platform for high-throughput, low-latency analog computing by exploiting engineered wave propagation to transform optical fields. However, implementing nonlinear mappings in optical hardware remains challenging. Here, we introduce a wavelength-multiplexed encoding-and-decoding (E+D) diffractive processor that exploits multiple illumination wavelengths to enhance the nonlinear function-approximation capability of a compact single-layer diffractive architecture, without cascading multiple diffractive layers or increasing the trainable degrees of freedom. Under sequential wavelength scanning, each wavelength-detector channel implements a distinct nonlinear function at the output of the diffractive processor. Numerical simulations using 100 wavelength channels and 10,000 spatial detector regions at the output of the diffractive processor demonstrate the implementation of one million distinct nonlinear functions through wavelength multiplexing. We also demonstrate a simultaneous multiwavelength illumination configuration in which the E+D diffractive processor performs wavelength-division multiplexing and nonlinear function approximation concurrently. This multiwavelength illumination configuration is experimentally validated by optically implementing 64 distinct nonlinear functions under simultaneous illumination at eight wavelengths from 495 to 635 nm. Through numerical simulations and visible-light experimental demonstrations, our results indicate that this wavelength-multiplexed nonlinear function approximation framework provides a scalable route toward compact, high-capacity diffractive processors for large-scale analog optical computing and optical information processing.
Comments27 Pages, 7 Figures
