Jove
Visualize
联系我们

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

The perspective of manual therapy as a fascia-directed biomechanical intervention in myofascial pain syndrome.

Frontiers in medicine·2026
Same author

Interpreting human sleep activity through neural contrastive learning.

Neuron·2026
Same author

Human hippocampal ripples prioritize model-based learning.

Neuron·2026
Same author

Trait anxiety is associated with reduced reward-related replay at rest.

Nature communications·2025
Same author

MetaIndux-TS: Frequency-Aware AIGC Foundation Model for Industrial Time Series.

IEEE transactions on neural networks and learning systems·2025
Same author

Industrial Foundation Model.

IEEE transactions on cybernetics·2025
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: Sep 19, 2025

Author Spotlight: Addressing Technical and Subjective Challenges in Measuring Classroom Attention
06:37

Author Spotlight: Addressing Technical and Subjective Challenges in Measuring Classroom Attention

Published on: December 15, 2023

4.2K

ABNN:具有动态激活量化用于工业健康状况预测的自适应门二元神经网络.

Lei Ren, Shixiang Li, Haiteng Wang

    IEEE transactions on neural networks and learning systems
    |June 17, 2025
    PubMed
    概括

    这项研究介绍了一种高效的自适应门二元神经网络 (ABNN),用于预测工业设备的健康状况. ABNN提高了准确性和效率,解决了边缘计算的局限性.

    科学领域:

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

    背景情况:

    • 工业设备健康预测对于安全性和可靠性至关重要.
    • 由于资源和实时限制,在工业边缘部署高精度深度学习模型具有挑战性.

    研究的目的:

    • 为工业边缘场景提出一个高效的自适应门二元神经网络 (ABNN).
    • 克服在资源有限的边缘环境中部署复杂的深度学习模型的局限性.

    主要方法:

    • 开发了一种趋势感知编码器 (TAE),用于优化输入层二元化.
    • 引入了一个可学习的精度指标 (LPI),用于适应性推理精度.
    • 设计了一个自适应式门卷积,以增强表达能力,而不会增加计算成本.
    • 实现了一个现场可编程网关阵列 (FPGA) 硬件加速器.

    主要成果:

    • 拟议的ABNN与基线模型相比,准确度大约提高了7%.
    • 与基线模型相比,ABNN显示了45%的效率提升.
    • 该网络有效地平衡了表示能力和计算效率.

    结论:

    更多相关视频

    A Single-Channel and Non-Invasive Wearable Brain-Computer Interface for Industry and Healthcare
    06:34

    A Single-Channel and Non-Invasive Wearable Brain-Computer Interface for Industry and Healthcare

    Published on: July 7, 2023

    2.5K
    Dynamic Digital Biomarkers of Motor and Cognitive Function in Parkinson's Disease
    10:28

    Dynamic Digital Biomarkers of Motor and Cognitive Function in Parkinson's Disease

    Published on: July 24, 2019

    15.4K

    相关实验视频

    Last Updated: Sep 19, 2025

    Author Spotlight: Addressing Technical and Subjective Challenges in Measuring Classroom Attention
    06:37

    Author Spotlight: Addressing Technical and Subjective Challenges in Measuring Classroom Attention

    Published on: December 15, 2023

    4.2K
    A Single-Channel and Non-Invasive Wearable Brain-Computer Interface for Industry and Healthcare
    06:34

    A Single-Channel and Non-Invasive Wearable Brain-Computer Interface for Industry and Healthcare

    Published on: July 7, 2023

    2.5K
    Dynamic Digital Biomarkers of Motor and Cognitive Function in Parkinson's Disease
    10:28

    Dynamic Digital Biomarkers of Motor and Cognitive Function in Parkinson's Disease

    Published on: July 24, 2019

    15.4K
    • ABNN提供了一种高效的解决方案,可以在边缘实时预测工业设备的健康状况.
    • 提出的方法可以在资源有限的环境中部署准确的深度学习模型.
    • 结合FPGA加速,ABNN框架显示出对工业边缘应用的重大前景.