Jove
Visualize
联系我们
JoVE
x logofacebook logolinkedin logoyoutube logo
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 JournalMethods CollectionsJoVE Encyclopedia of Experiments存档
教育
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab Manual教师资源中心教师网站
使用条款与条件
隐私政策
政策

相关实验视频

Updated: Jun 5, 2025

Transmission of Multiple Signals through an Optical Fiber Using Wavefront Shaping
09:43

Transmission of Multiple Signals through an Optical Fiber Using Wavefront Shaping

Published on: March 20, 2017

9.8K

使用多波长衍射深度神经网络进行光学多任务学习.

Zhengyang Duan1, Hang Chen1, Xing Lin1,2

  • 1Department of Electronic Engineering, Tsinghua University, Beijing 100084, China.

Nanophotonics (Berlin, Germany)
|December 5, 2024
PubMed
概括
此摘要是机器生成的。

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

Effects of Electric Field Dimensions on Electrokinetically Enhanced Cadmium Dissociation and Phytoremediation in Plateau Red Soil.

Plants (Basel, Switzerland)·2026
Same author

Opto-intelligence spectrometer using diffractive neural networks.

Nanophotonics (Berlin, Germany)·2024
Same author

Non-volatile photonic-electronic memory via 3D monolithic ferroelectric-silicon ring resonator.

Light, science & applications·2024
Same author

Partial coherence boosts photonic computing.

Light, science & applications·2024
Same author

Super-resolution diffractive neural network for all-optical direction of arrival estimation beyond diffraction limits.

Light, science & applications·2024
Same author

Demixing microwave signals using system-on-chip photonic processor.

Light, science & applications·2024
Same journal

Recent Progress in on-Demand Transfer-Enabled Integration of Wavelength-Scale Light Sources.

Nanophotonics (Berlin, Germany)·2026
Same journal

Tunable skyrmion bag textures in surface phonon polariton lattices.

Nanophotonics (Berlin, Germany)·2026
Same journal

All-Optical Diffractive Operators for Rapid, Computer-Free Morphological Transformations.

Nanophotonics (Berlin, Germany)·2026
Same journal

Tunable Skyrmion, Meron, and Skyrmion Bag Textures in Surface Phonon Polariton Lattices.

Nanophotonics (Berlin, Germany)·2026
Same journal

Deep-Subwavelength Slot-Enhanced Broadband Dynamic Camouflage Metasurface Across the S, C, X, and Ku Bands.

Nanophotonics (Berlin, Germany)·2026
Same journal

Machine Learning-Driven Cooling Window Design Beyond Hyperbolic Metamaterials.

Nanophotonics (Berlin, Germany)·2026
查看所有相关文章

本研究介绍了用于光学多任务学习的多波长衍射深度神经网络 (D2NN). 这些新型系统有效地并行执行多个人工智能任务,克服了单任务光子网络的局限性.

科学领域:

  • 神经形态光子计算的神经形态光子计算
  • 光学的人工智能 (AI)
  • 衍射深度神经网络 (D2NN) 是一种深度神经网络.

背景情况:

  • 现有的光子神经网络仅限于单个任务,阻碍了并行处理.
  • 当前架构中的任务竞争在尝试多任务学习时会降低性能.
  • 需要能够同时处理多个AI任务的集成光学系统.

研究的目的:

  • 提出一个新的光学多任务学习系统,使用多波长D2NN.
  • 在单个单一的系统中展示多个AI任务的并行处理.
  • 为了提高光子AI的计算吞吐量和准确性.

主要方法:

  • 设计了多波长衍射深度神经网络 (D2NN),并进行了联合优化.
  • 编码的多任务输入到不同的多波长通道.
  • 使用了包括MNIST,FMNIST,KMNIST和EMNIST在内的数据集进行分类任务.

主要成果:

  • 多波长D2NN在相同网络大小的多任务准确性方面明显优于单波长D2NN.
  • 拟议的系统有效地减轻了任务竞争,使高精度并行处理成为可能.
  • 较大的多波长D2NN可以达到与单独训练的单波长网络相提并论的准确性.
关键词:
衍射性深度神经网络是一种深度神经网络.多波长的光子神经网络这是光学多任务学习.

更多相关视频

Multi-Fiber Photometry to Record Neural Activity in Freely-Moving Animals
05:52

Multi-Fiber Photometry to Record Neural Activity in Freely-Moving Animals

Published on: October 20, 2019

36.0K
Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications
03:31

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications

Published on: December 15, 2023

468

相关实验视频

Last Updated: Jun 5, 2025

Transmission of Multiple Signals through an Optical Fiber Using Wavefront Shaping
09:43

Transmission of Multiple Signals through an Optical Fiber Using Wavefront Shaping

Published on: March 20, 2017

9.8K
Multi-Fiber Photometry to Record Neural Activity in Freely-Moving Animals
05:52

Multi-Fiber Photometry to Record Neural Activity in Freely-Moving Animals

Published on: October 20, 2019

36.0K
Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications
03:31

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications

Published on: December 15, 2023

468

结论:

  • 多波长D2NN为高通量光学多任务学习提供了可行的解决方案.
  • 这种方法为神经形态光子计算中的波长分割复杂化铺平了道路.
  • 开发的系统推动了能够并行执行任务的通用AI系统的发展.