Search research articles

关于 JoVE

概览领导团队博客 JoVE 帮助中心

作者

出版流程编辑委员会范围与政策同行评审常见问题投稿

图书馆员

用户评价订阅访问资源图书馆顾问委员会常见问题

研究

JoVE Journal Methods Collections JoVE Encyclopedia of Experiments 存档

教育

JoVE Core JoVE Business JoVE Science Education JoVE Lab Manual 教师资源中心教师网站

使用条款与条件

相关概念视频

您也可能阅读

相关文章

通过共同作者、期刊和引用图与本文相关的文章。

排序

Same author

Large-scale quantum communication networks with integrated photonics.

Nature·2026

Same author

Entanglement-controlled vectorial meta-holography.

Light, science & applications·2025

Same author

Complementary Superwetting Structures Treated by a Femtosecond Laser for Simultaneous Spontaneous Directional Transport of Water Droplets and Underwater Bubbles.

Langmuir : the ACS journal of surfaces and colloids·2024

Same author

Demonstration of hypergraph-state quantum information processing.

Nature communications·2024

Same author

Fractal photonic anomalous Floquet topological insulators to generate multiple quantum chiral edge states.

Light, science & applications·2023

Same author

Droplet-Driven Self-Propelled Devices Fabricated by a Femtosecond Laser.

ACS applied materials & interfaces·2023

Search research articles

相关实验视频

Updated: Sep 13, 2025

Transmission of Multiple Signals through an Optical Fiber Using Wavefront Shaping

Transmission of Multiple Signals through an Optical Fiber Using Wavefront Shaping

Published on: March 20, 2017

由物理驱动的自我监督网络实现的多重复合元光学的高速设计.

Yuqing He¹, Sheng Ye¹, Yue Han¹

¹State Key Laboratory for Mesoscopic Physics and Frontiers Science Center for Nano-optoelectronics & Collaborative Innovation Center of Quantum Matter, School of Physics, Peking University, Beijing, 100871, China.

Advanced science (Weinheim, Baden-Wurttemberg, Germany)

|July 31, 2025

概括

人工智能 (AI) 加快了元光学设计. 一个新的物理驱动的自我监督网络 (PDSS-Net) 能够实现超全息图的无代设计,将计算时间缩短1000倍以上.

关键词:

人工智能的人工智能是人工智能.高速的设计设计.这是一种meta-holography.多重复合的元光学.自主监督学习学习

更多相关视频

Demonstration of Spin-Multiplexed and Direction-Multiplexed All-Dielectric Visible Metaholograms

Demonstration of Spin-Multiplexed and Direction-Multiplexed All-Dielectric Visible Metaholograms

Published on: September 25, 2020

Microfluidic Platform with Multiplexed Electronic Detection for Spatial Tracking of Particles

Microfluidic Platform with Multiplexed Electronic Detection for Spatial Tracking of Particles

Published on: March 13, 2017

相关实验视频

Last Updated: Sep 13, 2025

Transmission of Multiple Signals through an Optical Fiber Using Wavefront Shaping

Transmission of Multiple Signals through an Optical Fiber Using Wavefront Shaping

Published on: March 20, 2017

Demonstration of Spin-Multiplexed and Direction-Multiplexed All-Dielectric Visible Metaholograms

Demonstration of Spin-Multiplexed and Direction-Multiplexed All-Dielectric Visible Metaholograms

Published on: September 25, 2020

Microfluidic Platform with Multiplexed Electronic Detection for Spatial Tracking of Particles

Microfluidic Platform with Multiplexed Electronic Detection for Spatial Tracking of Particles

Published on: March 13, 2017

科学领域:

光学和光子学在光学和光子学.
人工智能的人工智能
材料科学材料科学材料科学

背景情况:

人工智能 (AI) 通过预测元原子传输系数来加速元光学设计.
传统的超表面设计,特别是对元全息的设计,需要大量的优化代,从而导致较长的计算时间.
在元全息中修改目标图像需要重复整个设计过程.

研究的目的:

开发一个人工智能辅助的框架,大大加快元全息和其他元表面应用的设计过程.
引入一个能够进行无代推理的物理驱动的自我监督网络 (PDSS-Net).
为了证明网络对复杂,多重复合的元全息图的适应性.

主要方法:

提出了一个物理驱动的自我监督网络 (PDSS-Net),其中包含一个编码器-解码器模块.
训练网络建立输入全息图像和输出元原子结构参数之间的映射.
验证了网络在设计2K分辨率,三波长多重复合的元全息图和复杂多重复合的标量/矢量元全息图方面的性能.

主要成果:

在自我监督培训后,实现了对元全息图设计的无代推理.
在不到一秒的时间内完成了2K分辨率,三波长多重复合的元全息图的设计.
与传统优化方法相比,演示了超过1000倍的计算速度.
通过重新训练成功设计波长-极化-深度多重化标量和矢量元全息图.

结论:

PDSS-Net为元光学设计提供了一个无代的计算范式.
这种方法显著加速了多功能元表面的设计,包括复杂的元全息图.
开发的方法通过快速,可适应的智能设计来促进元设备的大规模应用.