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

Observational Learning01:12

Observational Learning

1.5K
Albert Bandura's observational learning, also known as imitation or modeling, occurs when a person observes and imitates another's behavior. It is a quicker process than operant conditioning. A well-known example is the Bobo doll study, where children who saw an adult acting aggressively towards the doll were more likely to act aggressively when left alone, compared to those who observed a nonaggressive adult. Many psychologists view observational learning as a form of latent learning...
1.5K

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

Predicting the progression risk of chronic obstructive pulmonary disease in high-risk individuals based on whole-lung radiomics and deep learning: a multicenter study.

Journal of thoracic disease·2026
Same author

A rare case of intramuscular granular cell tumor in the right thigh: case report and literature review.

Frontiers in medicine·2026
Same author

Multi-omics analysis identifies stemness-driven molecular subtypes, prognostic signature, epigenetic target APCDD1, and drug candidate Leflunomide in Wilms tumor.

Frontiers in oncology·2026
Same author

Development and validation of a multimodal clinical-radiomics-deep learning nomogram based on automated chest CT segmentation for classifying COPD severity: a multicenter study.

Frontiers in medicine·2026
Same author

Regional lymph node metastasis as a risk factor for recurrence in Borrmann type II gastric cancer: particular significance of the no. 7 lymph node.

Frontiers in oncology·2026
Same author

Modified Fuzheng Yiliu Decoction chemosensitizes colorectal cancer by inhibiting cancer stem cell metabolism and stemness through CAV1/ZNF460/GRP78 signaling.

Phytomedicine : international journal of phytotherapy and phytopharmacology·2026

相关实验视频

Updated: May 1, 2026

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications
03:31

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications

Published on: December 15, 2023

537

组建传导传播网络,用于半监督的少量学习.

Xueling Pan1,2, Guohe Li1,2, Yifeng Zheng3,4

  • 1Beijing Key Lab of Petroleum Data Mining, Department of Geophysics, China University of Petroleum, Beijing 102249, China.

Entropy (Basel, Switzerland)
|February 23, 2024
PubMed
概括

这项研究介绍了集体传导传播网络 (ETPN),这是一种利用未标记的数据和Dempster-Shafer (D-S) 证据融合的少数射击学习的新策略. ETPN提高了模型的准确性和稳定性,优于现有的几次学习方法.

关键词:
D-S 证据理论理论斯核函数的高斯核函数短暂的学习,即是少量学习.图表半监督部分监督标签传播 标签传播超级学习是一种超级学习.

更多相关视频

Author Spotlight: AI-Driven Trypanosome Species Detection from Microscopic Images
08:20

Author Spotlight: AI-Driven Trypanosome Species Detection from Microscopic Images

Published on: October 27, 2023

1.5K
Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique
04:48

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

Published on: July 5, 2024

401

相关实验视频

Last Updated: May 1, 2026

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications
03:31

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications

Published on: December 15, 2023

537
Author Spotlight: AI-Driven Trypanosome Species Detection from Microscopic Images
08:20

Author Spotlight: AI-Driven Trypanosome Species Detection from Microscopic Images

Published on: October 27, 2023

1.5K
Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique
04:48

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

Published on: July 5, 2024

401

科学领域:

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

背景情况:

  • 短暂的学习面临着有限的训练数据所带来的挑战,导致高差异,偏差和过度匹配.
  • 基于图形的传导性少数射击学习利用未标记的数据来改进预测,成为一个重要的研究领域.
  • 现有的方法很难有效地整合来自有限的标签和丰富的无标签数据的信息.

研究的目的:

  • 提出一个全新的集体半监督的少数射击学习策略,名为集体传导传播网络 (ETPN).
  • 提高未标记数据的利用率,提高少量学习模型的稳定性和准确性.
  • 通过整合传导网络和Dempster-Shafer证据融合来解决当前少数射击学习方法的局限性.

主要方法:

  • 开发了同质性和异质性集成传导传播网络,具有用于代推理的预设权重系数.
  • 改进了Dempster-Shafer (D-S) 证据融合,通过结合信息来实现稳定的多模型结果融合.
  • 改进了使用L2规范进行集成修剪,以选择准确的个体学习者,并引入了干扰集,以提高反干扰能力.

主要成果:

  • 拟议的集成传导传播网络 (ETPN) 与最先进的几次射击学习模型相比,表现出更高的性能.
  • 在miniImagNet和分层ImageNet上的5向5拍设置中,分别实现了0.3%和0.28%的精度改进.
  • 在miniImagNet和分层ImageNet的5路一拍设置中,显示了3.43%和7.6%的显著收益,突出显示了非常有限的数据的有效性.

结论:

  • 通过传导式学习和证据融合,ETPN有效地解决了少数人学习的挑战,通过强有力的利用未标记的数据.
  • 组合方法,DS理论和传导传播的新整合为少数拍摄分类提供了稳定而准确的方法.
  • 拟议的战略代表了少量学习的重大进步,特别是在标记样本稀缺的场景中.