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

Double Resonance Techniques: Overview

Double Resonance Techniques: Overview

Double resonance techniques in Nuclear Magnetic Resonance (NMR) spectroscopy involve the simultaneous application of two different frequencies or radiofrequency pulses to manipulate and observe two distinct nuclear spins. One important application of double resonance is spin decoupling, which selectively suppresses coupling with one type of nucleus while observing the NMR signal from another nucleus, simplifying the spectrum and enhancing resolution.
Spin decoupling is usually achieved by...

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

CauFinder: Steering Cell-State and Phenotype Transitions by Causal Disentanglement Learning.

Advanced science (Weinheim, Baden-Wurttemberg, Germany)·2026

Same author

Hybrid reservoir computing based on an external-cavity semiconductor ring laser.

Optics letters·2026

Same author

Coherent secure communication based on optical intensity-modulation injected semiconductor lasers.

Optics express·2025

Same author

Dynamic Network Driver Analysis Identifies Master Factors Associated with Progression of Solar Lentigines.

Biology·2025

Same author

Camrelizumab, an Anti-PD-1 Monoclonal Antibody, Plus Carboplatin and Nab-Paclitaxel as First-Line Setting for Extensive-Stage Small-Cell Lung Cancer: A Phase 2 Trial and Biomarker Analysis.

MedComm·2025

Same author

Hybrid readout scheme for time delay reservoir computing using a semiconductor laser.

Optics letters·2025

Search research articles

相关实验视频

Updated: Jun 17, 2025

Gradient Echo Quantum Memory in Warm Atomic Vapor

Gradient Echo Quantum Memory in Warm Atomic Vapor

Published on: November 11, 2013

光子深度残留时间延迟储存器计算计算

Changdi Zhou¹, Yu Huang¹, Yigong Yang¹

¹School of Optoelectronic Science and Engineering & Collaborative Innovation Center of Suzhou Nano Science and Technology, Soochow University, Suzhou 215006, China; Key Lab of Advanced Optical Manufacturing Technologies of Jiangsu Province & Key Lab of Modern Optical Technologies of Education Ministry of China, Soochow University, Suzhou 215006, China.

Neural networks : the official journal of the International Neural Network Society

|August 10, 2024

概括

我们介绍了一种新的深度残留时间延迟储存器计算 (DR-TDRC) 架构,该架构显著增强了内存功能和非线性通道均等. 这种光子方法可以扩展到许多层,提高人工智能应用的性能.

关键词:

深度学习是一种深度学习.深度神经网络是一个神经网络.机器学习机器学习储水库计算器储水库计算其余结构结构的残余结构.半导体激光器半导体激光器

更多相关视频

Quasi-light Storage for Optical Data Packets

Quasi-light Storage for Optical Data Packets

Published on: February 6, 2014

Generation and Coherent Control of Pulsed Quantum Frequency Combs

Generation and Coherent Control of Pulsed Quantum Frequency Combs

Published on: June 8, 2018

相关实验视频

Last Updated: Jun 17, 2025

Gradient Echo Quantum Memory in Warm Atomic Vapor

Gradient Echo Quantum Memory in Warm Atomic Vapor

Published on: November 11, 2013

Quasi-light Storage for Optical Data Packets

Quasi-light Storage for Optical Data Packets

Published on: February 6, 2014

Generation and Coherent Control of Pulsed Quantum Frequency Combs

Generation and Coherent Control of Pulsed Quantum Frequency Combs

Published on: June 8, 2018

科学领域:

光子学是一个光子学.
人工智能的人工智能
机器学习机器学习

背景情况:

时间延迟储库计算 (TDRC) 提供了一种简化的方法来处理反复的神经网络.
深度架构可以增强TDRC功能,但面临着层冗余的挑战.

研究的目的:

提出并展示一种具有增强功能的新型光子深度残留TDRC (DR-TDRC).
为了提高内存容量和非线性通道均衡性能.
为了实现可扩展的深度TDRC架构,增强稳定性.

主要方法:

开发一个光子深剩余TDRC (DR-TDRC) 架构,将剩余连接中的额外时间延迟纳入其中.
实施专门的剪切算法,以减轻深层结构中的性能退化.
使用基于注射锁分布式反激光器的960个神经元的4层DR-TDRC的实验演示.

主要成果:

在基准任务中,DR-TDRC表现优于传统的深层结构.
在内存能力和非线性通道均等 (几乎一个数量级) 中取得了显著的改进.
通过剪切算法成功将深度TDRC扩展到数十个层,从而提高了整体性能.

结论:

拟议的DR-TDRC为先进的深度光子计算提供了一种可行和可扩展的方法.
这项工作解决了深度TDRC的局限性,为更强大的AI硬件铺平了道路.
这些发现支持深度光子计算的扩展,以满足日益增长的人工智能需求.