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

Reducing Line Loss01:18

Reducing Line Loss

196
In a three-phase circuit, line loss is an indicator of energy dissipated as heat due to the resistance of transmission lines. To address this, incorporating transformers into the system—a step-up transformer at the source and a step-down transformer at the load—is a strategic solution. Two three-phase transformers are introduced to improve this.
With a step-up transformer at the source, the voltage is increased, thereby reducing the current in the transmission lines since power loss...
196
Downsampling01:20

Downsampling

260
When considering a sampled sequence with zero values between sampling instants, one can replace it by taking every N-th value of the sequence. At these integer multiples of N, the original and sampled sequences coincide. This process, known as decimation, involves extracting every N-th sample from a sequence, thereby creating a more efficient sequence.
The Fourier transform of the decimated sequence reveals a combination of scaled and shifted versions of the original spectrum. This...
260

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

LncRNA LOC728196/miR-513c axis facilitates glioma carcinogenesis by targeting TCF7.

Gene·2018
Same author

Tuning Cobalt and Nitrogen Co-Doped Carbon to Maximize Catalytic Sites on a Superabsorbent Resin for Efficient Oxygen Reduction.

ChemSusChem·2018
Same author

Comparative analysis of immune checkpoint inhibitors and chemotherapy in the treatment of advanced non-small cell lung cancer: A meta-analysis of randomized controlled trials.

Medicine·2018
Same author

Prediction of Occult Lymph Node Metastasis Using Tumor-to-Blood Standardized Uptake Ratio and Metabolic Parameters in Clinical N0 Lung Adenocarcinoma.

Clinical nuclear medicine·2018
Same author

TUSC3 accelerates cancer growth and induces epithelial-mesenchymal transition by upregulating claudin-1 in non-small-cell lung cancer cells.

Experimental cell research·2018
Same author

Deployment and Smokeless Tobacco Use Among Active Duty Service Members in the U.S. Military.

Military medicine·2018
Same journal

HardFlow: Hard-Constrained Sampling for Flow-Matching Models Via Trajectory Optimization.

IEEE transactions on pattern analysis and machine intelligence·2026
Same journal

Industrial Brain: Self-Evolving Neuro-Symbolic Autonomy with Causal Resilience for Cyber-Physical Systems.

IEEE transactions on pattern analysis and machine intelligence·2026
Same journal

Adaptive Hardness-Driven Dictionary Distillation for Incomplete Streaming View Clustering.

IEEE transactions on pattern analysis and machine intelligence·2026
Same journal

Mixture of Global and Local Experts with Diffusion Transformer for Controllable Face Generation.

IEEE transactions on pattern analysis and machine intelligence·2026
Same journal

Task-KV: Task-aware KV Cache Optimization via Semantic Differentiation of Attention Heads.

IEEE transactions on pattern analysis and machine intelligence·2026
Same journal

Achieving Text-based Person Retrieval with Any Granularity.

IEEE transactions on pattern analysis and machine intelligence·2026
查看所有相关文章

相关实验视频

Updated: Sep 16, 2025

Optimized Fabrication Procedure for High-Quality Graphene-based Moiré Superlattice Devices
11:24

Optimized Fabrication Procedure for High-Quality Graphene-based Moiré Superlattice Devices

Published on: July 11, 2025

6.5K

有效的扭曲最小化的层次修剪.

Kaixin Xu, Zhe Wang, Runtao Huang

    IEEE transactions on pattern analysis and machine intelligence
    |July 7, 2025
    PubMed
    概括
    此摘要是机器生成的。

    这项研究引入了一种新的深度神经网络 (DNN) 的训练后修剪框架,可以最大限度地减少输出扭曲. 该方法在各种模型和任务中实现了浮点运算 (FLOP) 的显著减少,而不会影响准确性.

    更多相关视频

    Author Spotlight: Optimization of Processing Technology for Tiebangchui with Zanba Based on CRITIC Combined with Box-Behnken Response Surface Method
    09:16

    Author Spotlight: Optimization of Processing Technology for Tiebangchui with Zanba Based on CRITIC Combined with Box-Behnken Response Surface Method

    Published on: May 12, 2023

    1.2K
    Detection of Architectural Distortion in Prior Mammograms via Analysis of Oriented Patterns
    13:44

    Detection of Architectural Distortion in Prior Mammograms via Analysis of Oriented Patterns

    Published on: August 30, 2013

    43.0K

    相关实验视频

    Last Updated: Sep 16, 2025

    Optimized Fabrication Procedure for High-Quality Graphene-based Moiré Superlattice Devices
    11:24

    Optimized Fabrication Procedure for High-Quality Graphene-based Moiré Superlattice Devices

    Published on: July 11, 2025

    6.5K
    Author Spotlight: Optimization of Processing Technology for Tiebangchui with Zanba Based on CRITIC Combined with Box-Behnken Response Surface Method
    09:16

    Author Spotlight: Optimization of Processing Technology for Tiebangchui with Zanba Based on CRITIC Combined with Box-Behnken Response Surface Method

    Published on: May 12, 2023

    1.2K
    Detection of Architectural Distortion in Prior Mammograms via Analysis of Oriented Patterns
    13:44

    Detection of Architectural Distortion in Prior Mammograms via Analysis of Oriented Patterns

    Published on: August 30, 2013

    43.0K

    科学领域:

    • 计算机科学 计算机科学
    • 人工智能的人工智能
    • 机器学习 机器学习

    背景情况:

    • 深度神经网络 (DNN) 是计算密集型的,需要高效的模型压缩方法.
    • 修剪是一种减少模型大小和复杂性的技术,在优化层次减少和最小化输出扭曲方面经常面临挑战.

    研究的目的:

    • 开发一个培训后修剪框架,共同优化层级修剪,以尽量减少模型输出扭曲.
    • 为了利用输出扭曲的新发现的附加性属性,以实现高效的修剪优化.

    主要方法:

    • 建议采用训练后修剪框架,优化层级修剪以最大限度地减少模型输出扭曲.
    • 在DNN中确定并利用输出扭曲的附加性属性.
    • 修剪优化被重新阐述为一个通过动态编程解决的组合式问题,实现线性时间复杂性.
    • 采用基于Hessian的泰勒近似来优化扭曲,提高修剪效率.

    主要成果:

    • 该框架实现了最先进的 (SoTA) 结果,在各种DNN架构 (CNNs,ViTs) 和任务 (图像分类,3D对象检测) 中显著减少了FLOP.
    • 例如,在CIFAR-10 (VGG-16) 上减少了多达29.2倍的FLOP,在ImageNet (DeiT-Base) 上减少了2倍的FLOP,没有精度损失.
    • 在3D物体检测模型中也观察到显著的FLOP减少,例如CenterPoint (3.89x) 和PVRCNN (3.72x).

    结论:

    • 拟议的层适应性重量修剪框架是有效和实用的,用于提高模型性能.
    • 该方法在不降低准确度的情况下显示了显著的计算节约 (FLOP减少).
    • 基于添加性属性的动态编程方法为DNN修剪提供了快速有效的解决方案.