[光计算与人工智能]论文阅读2:All-optical machine learning using diffractive deep neural networks 努力加油的维克 光计算,计算摄影学36 人赞同了该文章 从这篇开始是衍射神经网络的相关笔记。 论文原地址如下,来自Science正刊。 https://www.science.org/doi/10.1126/science.aat8084www.science.org/doi/...
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。
As an analogy to standard deep neural networks (see Fig. 1D), one can consider the transmission/reflection coefficient of each point/neuron as a multiplicative “bias” term, which is a learnable network parameter that is iteratively adjusted during the training process of the diffractive network,...
We utilized deep learning-based optimization with stochastic gradient descent to optimize the thickness values of the diffractive features on the diffractive layers. This training was targeted at minimizing a custom-designed loss function defined by the mean squared error (MSE) between the diffractive ...
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 the speed of light. Prototype of a broadband diffrac...
(i.e., neurons) of diffractive surfaces are adjusted or trained to perform a desired input–output transformation task as the light diffracts through these layers. Trained with deep-learning-based error back-propagation methods, these diffractive networks have been shown to perform machine-learning ...
Qtera Corp. of Boca Raton, Fla., and Qwest Communications International Inc. of Denver have completed a 30-day field trial of an all-optical network. The system transmitted 10-Gb/s signals over 2400 km of fiber without the need for optoelectronic regeneration. Qtera supplied transmitters for...
Optical nonlinear functions are crucial for various applications in integrated photonics, including all-optical information processing1, photonic neural networks2,3 and on-chip ultrafast light sources4,5. However, the weak native nonlinearity of most nan