arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2409.20346physics.app-phphysics.optics
收藏

基于线性衍射处理器的全光自编码器机器学习框架

All-optical autoencoder machine learning framework using linear diffractive processors

Peijie Feng, Yong Tan, Mingzhe Chong, Lintao Li, Zongkun Zhang, Fubei Liu, Yunhua Tan, Yongzheng Wen

AI总结:

本研究提出基于线性衍射处理器的全光自编码器框架,利用D2NN双向复用特性实现编解码,拓展了潜在空间应用,验证了图像去噪等多场景功能,为多功能光学智能系统提供新思路。

摘要:

衍射深度神经网络(D2NN)以其高速和强并行性著称,已被广泛应用于模式识别、图像处理和图像传输等多个领域。然而,现有网络架构主要聚焦于原始域内的数据表示,对潜在空间的探索有限,从而限制了D2NN的信息挖掘能力和多功能集成。在此,我们提出一种全光自编码器(OAE)框架,该框架将输入波场线性编码为衍射潜在空间(DLS)中的先验形状分布,并将编码后的图案解码回原始波场。利用D2NN的双向复用特性,OAE模型在波传播的一个方向上充当编码器,在相反方向上充当解码器。我们进一步将该模型应用于三个关键领域:图像去噪、抗噪声可重构图像分类和图像生成。我们开展了概念验证实验以验证数值模拟结果。我们的OAE框架充分挖掘了潜在表示的潜力,使得单组衍射处理器能够同时实现图像重建、表示和生成。这项工作不仅为光学生成模型的设计提供了全新见解,也为开发多功能、高度集成的通用光学智能系统铺平了道路。

英文摘要:

Diffractive deep neural network (D2NN), known for its high speed and strong parallelism, has been widely applied across various fields, including pattern recognition, image processing, and image transmission. However, existing network architectures primarily focus on data representation within the original domain, with limited exploration of the latent space, thereby restricting the information mining capabilities and multifunctional integration of D2NNs. Here, we propose an all-optical autoencoder (OAE) framework that linearly encodes the input wavefield into a prior shape distribution in the diffractive latent space (DLS) and decodes the encoded pattern back to the original wavefield. By leveraging the bidirectional multiplexing property of D2NN, the OAE models function as encoders in one direction of wave propagation and as decoders in the opposite direction. We further apply the models to three key areas: image denoising, noise-resistant reconfigurable image classification, and image generation. Proof-of-concept experiments have been conducted to validate numerical simulations. Our OAE framework fully exploits the potential of latent representations, enabling a single set of diffractive processors to simultaneously achieve image reconstruction, representation, and generation. This work not only offers fresh insights into the design of optical generative models but also paves the way for developing multifunctional, highly integrated, and general optical intelligent systems.

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。

↑