在这里,我们介绍了一种物理机制,通过演示全光学衍射深度神经网络(D2NN, diffractive deep neural network)架构来执行机器学习,该架构可以使用基于深度学习的设计的集成工作的被动衍射层实现各种功能。我们创建了3D打印的D2NN,它实现了手写数字和时尚产品图像的分类,以及太赫兹光谱成像镜头的功能。 我们的全光学深度学习框...
Using a 3D printer, a research team at the UCLA Samueli School of Engineering has created an artificial neural network that can analyze large volumes of data and identify objects at the speed of light. Called a diffractive deep neural network (D2NN), the technology uses the light scattering ...
(2018)All-optical machine learning using diffractive deep neural networks,程序员大本营,技术文章内容聚合第一站。
OPTICAL computingIMAGE recognition (Computer vision)COMPUTED tomographyIMAGE processingA deep diffractive neural network (D2NN) is a fast optical computing structure that has been widely used in image classification, logical operations, and other fields. Computed tomography (CT) imaging is a reliabl...
系统标签: diffractive deep optical neural learning networks Seediscussions,stats,andauthorprofilesforthispublicationat:https://.researchgate.net/publication/324745055All-OpticalMachineLearningUsingDiffractiveDeepNeuralNetworksArticle in Science·April2018DOI:10.1126/science.aat8084CITATIONS60READS7596authors,including...
These diffractive layers are positioned in a cascaded manner along the optical axis, resulting in a total axial length of 150\(\lambda\) for the entire design. A complex input object, \(i(x,y)=A(x,y){e}^{j\phi (x,y)}\), illuminated at \(\lambda\) is placed at the input ...
Fig. 1: Schematic of polarization-multiplexed all-optical diffractive computing. aOptical layout of the polarization-encoded diffractive network, where four isotropic diffractive layers and one array of linear polarizers are jointly used to perform two distinct, complex-valued linear transformations between...
SmartGlass (SG) is a python implementation of a diffractive optical neural network. Currently, it supports training an all-optical classifier (e.g. classify hand-written digits MNIST dataset). Besides, the framework can also be used to design optics based on a task like focusing and beam steer...
A diffractive deep neural network is an optical machine learning structure that is capable of combining deep learning with optical diffraction and light-matter interaction to design diffractive surfaces that collectively carry out optical computation at
As an optical-based classifier of the physical neural network, the independent diffractive deep neural network (D2NN) can be utilized to learn the single-view spatial featured mapping between the input lightfields and the truth labels by preprocessing a large number of training samples. However, ...