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

Non-equilibrium in the Cell01:16

Non-equilibrium in the Cell

5.3K
An important concept in studying metabolism and energy is that of chemical equilibrium. Most chemical reactions are reversible. They can proceed in both directions, releasing energy into their environment in one direction, and absorbing it from the environment in the other direction. The same is true for the chemical reactions involved in cell metabolism, such as the breaking down and building up of proteins into and from individual amino acids, respectively. Reactants within a closed system...
5.3K
Survival Tree01:19

Survival Tree

388
Survival trees are a non-parametric method used in survival analysis to model the relationship between a set of covariates and the time until an event of interest occurs, often referred to as the "time-to-event" or "survival time." This method is particularly useful when dealing with censored data, where the event has not occurred for some individuals by the end of the study period, or when the exact time of the event is unknown.
 Building a Survival Tree
Constructing a...
388
Natural Selection and Adaptation01:15

Natural Selection and Adaptation

1.2K
Natural selection, a fundamental concept in evolutionary biology, is the mechanism by which evolution is driven, favoring organisms that are best adapted to their environments. This process enhances their chances of survival and reproduction. Adaptation, a key outcome of this process, involves genetic modifications that optimize an organism's functionality under specific environmental challenges, such as extreme cold or thinner air at high altitudes.
Beyond physical adaptations,...
1.2K

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

Early-life musical intervention programs neuroimmune activity and synaptic plasticity to enhance adult learning and memory.

Brain, behavior, and immunity·2026
Same author

The transcriptional regulator MOS1 attenuates salinity stress-induced seed germination inhibition via negative feedback regulation of ABA signaling in Arabidopsis.

Journal of experimental botany·2026
Same author

Cepharanthine triggers immunogenic cell death in solid tumors by suppressing protein kinase C zeta-mediated poly(ADP-ribose) polymerase 1 expression and synergizes with immunotherapy.

Phytomedicine : international journal of phytotherapy and phytopharmacology·2026
Same author

Gut microbiota may influence Sjögren's syndrome risk through immune cell mediation: A Mendelian randomization analysis.

Medicine·2026
Same author

The HIRA-interacting histone chaperone CABIN1 negatively regulates plant immunity mediated by immune receptor gene SNC1.

Plant physiology·2026
Same author

CXCL16-driven CD4<sup>+</sup> T cells orchestrate immunosurveillance against MHC-I-deficient hepatocellular tumors.

Journal for immunotherapy of cancer·2026

相关实验视频

Updated: Jan 16, 2026

Visualizing Visual Adaptation
04:43

Visualizing Visual Adaptation

Published on: April 24, 2017

9.6K

低级适应边缘AI的低级适应.

Zhixue Wang1, Hongyao Ma2, Jiahui Zhai2

  • 1Shandong Jiaotong University, Haitang Road 5001, 250357, Jinan, China. zhixue.w@163.com.

Scientific reports
|September 26, 2025
PubMed
概括

低级适应边缘人工智能 (LoRAE) 在资源有限的边缘设备上高效地更新人工智能 (AI) 模型. 这种方法显著减少了可训练的参数,同时保持了各种AI任务的高模型准确性.

科学领域:

  • 人工智能的人工智能
  • 机器学习 机器学习
  • 计算机视觉 计算机视觉
  • 边缘计算 边缘计算

背景情况:

  • 边缘人工智能 (AI) 提供了变革性的应用,但在资源有限的设备上更新模型方面面临挑战.
  • 边缘设备上的模型更新受到计算和通信能力的限制的阻碍.
  • 现有的模型更新方法通常需要大量的计算和通信资源,这使得它们不适合边缘环境.

研究的目的:

  • 引入一种新的方法,即Low-Rank Adaptation for Edge AI (LoRAE),旨在应对边缘设备上更新人工智能模型的挑战.
  • 显著减少模型更新所需的可训练参数数量,从而最大限度地降低计算和通信开销.
  • 评估LoRAE在边缘设备上的各种AI任务中保持或提高模型准确性的有效性.

主要方法:

  • LoRAE利用卷积神经网络 (CNN) 重量矩阵的低级分解来减少更新参数的数量.
  • 与传统的全参数更新相比,该方法将可训练参数减少到大约4%.
  • 使用YOLOv8x模型对图像分类,物体检测和图像细分任务进行了实验.

主要成果:

  • LoRAE实现了实质性的参数减少:图像分类为86.1%,对象检测为98.6%,图像分割为94.1%.
关键词:
边缘AI 边缘AI适应低级别的适应.模型更新效率效率 模型更新效率降低参数减少的方法

更多相关视频

Evidence-based Knowledge Synthesis and Hypothesis Validation: Navigating Biomedical Knowledge Bases via Explainable AI and Agentic Systems
05:47

Evidence-based Knowledge Synthesis and Hypothesis Validation: Navigating Biomedical Knowledge Bases via Explainable AI and Agentic Systems

Published on: June 13, 2025

1.3K

相关实验视频

Last Updated: Jan 16, 2026

Visualizing Visual Adaptation
04:43

Visualizing Visual Adaptation

Published on: April 24, 2017

9.6K
Evidence-based Knowledge Synthesis and Hypothesis Validation: Navigating Biomedical Knowledge Bases via Explainable AI and Agentic Systems
05:47

Evidence-based Knowledge Synthesis and Hypothesis Validation: Navigating Biomedical Knowledge Bases via Explainable AI and Agentic Systems

Published on: June 13, 2025

1.3K
  • 这些可训练参数的显著减少在不损害模型准确性,并在某些情况下提高模型准确性的情况下实现.
  • 该方法有效地减轻了与边缘设备上更新AI模型相关的计算和通信挑战.
  • 结论:

    • 在资源有限的边缘环境中,LoRAE为更新人工智能模型提供了一个高效和精确的解决方案.
    • 该方法展示了通过优化模型更新在边缘设备上部署先进AI功能的可行性.
    • LoRAE具有很大的潜力,可以在各种应用中推进边缘AI的实际实施.