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

Nonlinear optical vector processing using linear silicon photonic circuits for 50 Gb/s memory and string similarity functions.

Nature communications·2025
Same author

Si<sub>3</sub>N<sub>4</sub>-plasmonic ferroelectric MZIR modulator for 112-Gbaud PAM-4 transmission in the O-band.

Optics express·2023
Same author

Efficient multi-step coupling between Si<sub>3</sub>N<sub>4</sub> waveguides and CMOS plasmonic ferroelectric phase shifters in the O-band.

Optics express·2022
Same author

Quantization-aware training for low precision photonic neural networks.

Neural networks : the official journal of the International Neural Network Society·2022
Same author

Noise-resilient and high-speed deep learning with coherent silicon photonics.

Nature communications·2022
Same author

Channel response-aware photonic neural network accelerators for high-speed inference through bandwidth-limited optics.

Optics express·2022

相关实验视频

Updated: Jan 17, 2026

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

10.3K

使用WDM SiGe EAM阵列切片的时空波长复杂光子张力芯.

A Prapas, M Moralis-Pegios, A Tsakyridis

    Optics express
    |September 23, 2025
    PubMed
    概括
    此摘要是机器生成的。

    光子神经网络 (PNN) 提供节能的人工智能加速. 这项研究展示了用于AI工作负载的8x8光子集成张量核心 (PITC) 架构,在基准数据集上实现了高分类准确性.

    更多相关视频

    A Photonic System for Generating Unconditional Polarization-Entangled Photons Based on Multiple Quantum Interference
    07:56

    A Photonic System for Generating Unconditional Polarization-Entangled Photons Based on Multiple Quantum Interference

    Published on: September 5, 2019

    8.9K
    Demonstration of Spin-Multiplexed and Direction-Multiplexed All-Dielectric Visible Metaholograms
    08:48

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

    Published on: September 25, 2020

    6.2K

    相关实验视频

    Last Updated: Jan 17, 2026

    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

    10.3K
    A Photonic System for Generating Unconditional Polarization-Entangled Photons Based on Multiple Quantum Interference
    07:56

    A Photonic System for Generating Unconditional Polarization-Entangled Photons Based on Multiple Quantum Interference

    Published on: September 5, 2019

    8.9K
    Demonstration of Spin-Multiplexed and Direction-Multiplexed All-Dielectric Visible Metaholograms
    08:48

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

    Published on: September 25, 2020

    6.2K

    科学领域:

    • 光子学是指光子学的使用方法.
    • 人工智能的人工智能
    • 集成电路 集成电路

    背景情况:

    • 光子神经网络 (PNN) 正在成为下一代人工智能平台.
    • 它们通过利用光的并行性,在计算能量和面积效率方面提供了显著的进步.
    • 通过空间,波长和时间利用光是PNN潜力的关键.

    研究的目的:

    • 介绍一个新的光子集成张量核 (PITC) 架构.
    • 通过实验验证PITC架构对AI基准工作负载进行验证.
    • 在基于芯片的光子设置中演示多波长数据和重量编码.

    主要方法:

    • 开发了一个 8x8 PITC 架构,将一个支持 AWGR 的 PNN 与一个 SiGe EAM 阵列相结合.
    • 使用基于芯片的光子加速器设置.
    • 实验验证了使用AI基准工作负载在20Gbaud的架构.

    主要成果:

    • 使用PITC架构成功对IRIS和MNIST数据集进行了分类.
    • 获得了科恩的kappa分数,IRIS的0.8438和MNIST的0.7421分.
    • 证明了拟议的PITC架构对AI应用的可行性.

    结论:

    • 该PITC架构显示了对高效AI加速的承诺.
    • 实验验证证证实了集成光子学对人工智能的潜力.
    • 这项工作为先进的光子AI硬件铺平了道路.