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

LSTM networks provide efficient cyanobacterial blooms forecasting even with incomplete spatio-temporal data.

Water research·2024
Same author

Artificial Intelligence Techniques for Automatic Detection of Peri-implant Marginal Bone Remodeling in Intraoral Radiographs.

Journal of digital imaging·2023
Same author

Hierarchical Mission Planning with a GA-Optimizer for Unmanned High Altitude Pseudo-Satellites.

Sensors (Basel, Switzerland)·2021
Same author

Automatic computation of mandibular indices in dental panoramic radiographs for early osteoporosis detection.

Artificial intelligence in medicine·2020
Same author

Structural correlates of apathy in Alzheimer's disease: a multimodal MRI study.

International journal of geriatric psychiatry·2016
Same author

Sensors and technologies in Spain: state-of-the-art.

Sensors (Basel, Switzerland)·2014
Same journal

A practical design of backdoor trigger under frequency-based orthogonality constraints.

Neural networks : the official journal of the International Neural Network Society·2026
Same journal

EEG fine-grained visual semantic decoding via a multimodal framework.

Neural networks : the official journal of the International Neural Network Society·2026
Same journal

Collaborative-adversarial jailbreaking: A propagation-aware attack framework for multi-agent code generation systems.

Neural networks : the official journal of the International Neural Network Society·2026
Same journal

Theoretical analysis of the denoising autoencoder using Tweedie's formula.

Neural networks : the official journal of the International Neural Network Society·2026
Same journal

Frequency-based cross-attention fusion network for RGB-D salient object detection.

Neural networks : the official journal of the International Neural Network Society·2026
Same journal

HTNet: A self-supervised heterogeneous triple network for multi-modal data.

Neural networks : the official journal of the International Neural Network Society·2026
查看所有相关文章

相关实验视频

Updated: Jul 11, 2025

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography
04:48

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography

Published on: November 30, 2022

2.8K

在语义图像分割中的卷积神经网络的过器修剪.

Clara I López-González1, Esther Gascó1, Fredy Barrientos-Espillco2

  • 1Department of Software Engineering and Artificial Intelligence, Complutense University of Madrid, Madrid, 28040, Spain.

Neural networks : the official journal of the International Neural Network Society
|November 17, 2023
PubMed
概括
此摘要是机器生成的。

本研究为卷积神经网络 (CNN) 引入了新的过器和层修剪方法,显著减少模型大小和计算负载,同时保持或提高准确性. 这些可解释的AI技术为资源有限的环境提供了高效的模型压缩.

关键词:
卷积神经网络 (CNN) 是一种神经网络.可解释的人工智能 (xAI)过器的修剪 过器的修剪图像细分的图像细分.模型的压缩压缩.主要组成部分分析 (PCA)

更多相关视频

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique
04:48

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

Published on: July 5, 2024

409
Deep Learning-Based Segmentation of Cryo-Electron Tomograms
10:25

Deep Learning-Based Segmentation of Cryo-Electron Tomograms

Published on: November 11, 2022

8.8K

相关实验视频

Last Updated: Jul 11, 2025

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography
04:48

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography

Published on: November 30, 2022

2.8K
Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique
04:48

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

Published on: July 5, 2024

409
Deep Learning-Based Segmentation of Cryo-Electron Tomograms
10:25

Deep Learning-Based Segmentation of Cryo-Electron Tomograms

Published on: November 11, 2022

8.8K

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:

  • 卷积神经网络 (CNN) 对实时应用至关重要,但需要大量资源.
  • 现有的CNN压缩方法通常需要广泛的培训,并忽视数据的影响.
  • 在边缘设备和实时系统上部署资源高效的人工智能至关重要.

研究的目的:

  • 开发有效和可解释的方法来压缩卷积神经网络 (CNN).
  • 调查数据对模型压缩和性能的影响.
  • 介绍适用于各种CNN架构的新型修剪策略.

主要方法:

  • 提出了两种使用主要组件分析 (PCA) 和下一个卷积影响度量的过器修剪方法.
  • 专门为U-Net架构引入了一个层修剪方法.
  • 实施了微调策略,以恢复修剪后的模型通用化.
  • 开发了一种基于重要性分数分布的方法,使用平均标准偏差和影响度量.

主要成果:

  • 在U-Net (98.7%和97.5%),DeepLabv3+ (46.5%和51.9%),SegNet (72.4%和83.6%) 和VGG-16 (86.5%和82.2%) 上实现了显著的参数和FLOP降低.
  • 在所有测试模型和数据集中保持或提高准确性,包括U-Net.Net的0.35%增长.
  • 在不同的CNN和语义细分任务中展示了裁剪策略的通用适用性.

结论:

  • 开发的修剪方法有效地减少了CNN的复杂性,而不会影响准确性.
  • 可解释的人工智能 (xAI) 背景为数据和模型性能之间的关系提供了洞察力.
  • 这些技术为在资源有限的平台上部署高性能CNN提供了可行的解决方案.