Jove
Visualize
お問い合わせ
JoVE
x logofacebook logolinkedin logoyoutube logo
JoVEについて
概要リーダーシップブログJoVEヘルプセンター
著者向け
出版プロセス編集委員会範囲と方針査読よくある質問投稿
図書館員向け
推薦の声購読アクセスリソース図書館諮問委員会よくある質問
研究
JoVE JournalMethods CollectionsJoVE Encyclopedia of Experimentsアーカイブ
教育
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab Manual教員リソースセンター教員サイト
利用規約
プライバシーポリシー
ポリシー

関連する概念動画

Confounding in Epidemiological Studies01:27

Confounding in Epidemiological Studies

612
Confounding in statistical epidemiology represents a pivotal challenge, referring to the distortion in the perceived relationship between an exposure and an outcome due to the presence of a third variable, known as a confounder. This variable is associated with both the exposure and the outcome but is not a direct link in their causal chain. Its presence can lead to erroneous interpretations of the exposure's effect, either exaggerating or underestimating the true association. This...
612
Strategies for Assessing and Addressing Confounding01:25

Strategies for Assessing and Addressing Confounding

372
Confounding is a critical issue in epidemiological studies, often leading to misleading conclusions about associations between exposures and outcomes. It occurs when the relationship between the exposure and the outcome is mixed with the effects of other factors that influence the outcome. Given that, addressing confounding is of high importance for drawing accurate inferences in research.
Confounding can be addressed at both the design phase of a study and through analytical methods after data...
372
Normal Stress01:19

Normal Stress

1.4K
Normal stress is a type of stress that occurs when forces act perpendicular, or normal, to a material's cross-sectional area. This stress often arises in structures when subjected to axial loading, which is the application of force along the axis of an object. A practical example of this can be found in bridge truss members.
When a rod is under axial loading, the internal forces and corresponding stress are normal to the plane of the section, so it is termed normal stress. It's important to...
1.4K
Normal Distribution01:11

Normal Distribution

16.7K
The normal, a continuous distribution, is the most important of all the distributions. Its graph is a bell-shaped symmetrical curve, which is observed in almost all disciplines. Some of these include psychology, business, economics, the sciences, nursing, and, of course, mathematics. Some instructors may use the normal distribution to help determine students’ grades. Most IQ scores are normally distributed. Often real-estate prices fit a normal distribution. The normal distribution is...
16.7K
Normal and Shear Force01:14

Normal and Shear Force

3.3K
When a beam is subjected to different loads, such as weight, pressure, or other external forces, internal forces are generated within the beam. These forces can have a significant impact on the overall stability and strength of the structure. Engineers use various methods to analyze and determine the magnitude and direction of these internal forces. One common technique used to determine internal forces in beams is the method of sections. This method involves considering an imaginary point or...
3.3K
Avoidance Learning and Learned Helplessness01:14

Avoidance Learning and Learned Helplessness

2.5K
Avoidance learning and learned helplessness are critical concepts in understanding behavioral responses to negative stimuli.
Avoidance learning occurs when an organism learns that a specific behavior can prevent an unpleasant outcome. For example, a student who receives a bad grade may start studying harder to avoid future poor grades. This behavior persists even when the negative outcome is no longer present. Avoidance learning is powerful because it maintains behavior in the absence of the...
2.5K

こちらも読む

関連記事

共著者、ジャーナル、引用グラフによってこの研究に関連する記事。

並び替え
Same author

Ground truthing marine litter stranding hotspots for the Eastern Pacific Ocean coasts: A collaborative approach with school communities.

Journal of environmental management·2026
Same author

Reclone: a global research community building equitable access to reagents.

Nature methods·2026
Same author

Leveraging Machine Learning to Advance Alcohol Research: Current Applications, Challenges, and Opportunities.

Alcohol research : current reviews·2026
Same author

Small-molecule inhibitors of the protein kinase DYRK as potential therapeutic candidates in cancer.

Cell chemical biology·2026
Same author

A framework of digital biomarkers for neurodegenerative diseases.

Nature reviews bioengineering·2026
Same author

SocialGen: Modeling Multi-Human Social Interaction with Language Models.

Proceedings. International Conference on 3D Vision·2026
Same journal

VFMStitch: A Vision-Foundation-Model Empowered Framework for 3D Ultrasound Stitching via Geometric-Semantic Feature Fusion.

Proceedings of machine learning research·2026
Same journal

What do LLMs value? An evaluation framework for revealing subjective trade-offs in assessment of glycemic control.

Proceedings of machine learning research·2026
Same journal

Towards the Efficient Inference by Incorporating Automated Computational Phenotypes under Covariate Shift.

Proceedings of machine learning research·2026
Same journal

Endo-SemiS: Towards Robust Semi-Supervised Image Segmentation for Endoscopic Video.

Proceedings of machine learning research·2026
Same journal

Perspective: Machine Learning for Health Should Consider Social Drivers of Health.

Proceedings of machine learning research·2026
Same journal

Classifying Phonotrauma Severity from Vocal Fold Images with Soft Ordinal Regression.

Proceedings of machine learning research·2026
関連記事をすべて見る

関連する実験動画

Updated: Jan 24, 2026

Operant Learning of Drosophila at the Torque Meter
17:31

Operant Learning of Drosophila at the Torque Meter

Published on: June 16, 2008

14.0K

再帰的特徴正規化による交絡因子フリーの継続学習

Yash Shah1, Camila Gonzalez1, Mohammad H Abbasi1

  • 1Stanford University, Stanford, United States.

Proceedings of machine learning research
|January 23, 2026
PubMed
まとめ
この要約は機械生成です。

本研究では、継続学習における交絡変数の影響に対処するため、再帰的メタデータ正規化（R-MDN）レイヤーを導入します。R-MDNは、時間とともに変化する交絡因子によって引き起こされるモデルの忘却を軽減することにより、グループ間のより公平な予測を保証します。

キーワード:
継続学習交絡変数特徴正規化破滅的忘却公平性再帰的メタデータ正規化

さらに関連する動画

Quantifying Learning in Young Infants: Tracking Leg Actions During a Discovery-learning Task
11:18

Quantifying Learning in Young Infants: Tracking Leg Actions During a Discovery-learning Task

Published on: June 1, 2015

11.1K
Fully Automated Leg Tracking in Freely Moving Insects using Feature Learning Leg Segmentation and Tracking FLLIT
08:04

Fully Automated Leg Tracking in Freely Moving Insects using Feature Learning Leg Segmentation and Tracking FLLIT

Published on: April 23, 2020

7.2K

関連する実験動画

Last Updated: Jan 24, 2026

Operant Learning of Drosophila at the Torque Meter
17:31

Operant Learning of Drosophila at the Torque Meter

Published on: June 16, 2008

14.0K
Quantifying Learning in Young Infants: Tracking Leg Actions During a Discovery-learning Task
11:18

Quantifying Learning in Young Infants: Tracking Leg Actions During a Discovery-learning Task

Published on: June 1, 2015

11.1K
Fully Automated Leg Tracking in Freely Moving Insects using Feature Learning Leg Segmentation and Tracking FLLIT
08:04

Fully Automated Leg Tracking in Freely Moving Insects using Feature Learning Leg Segmentation and Tracking FLLIT

Published on: April 23, 2020

7.2K

科学分野:

  • 人工知能
  • 機械学習
  • コンピュータサイエンス

背景:

  • 交絡変数は、機械学習モデルにおける偽の相関関係を導入し、予測を偏らせます。
  • メタデータ正規化（MDN）などの既存の方法は、特徴分布を調整しますが、継続学習には苦労します。
  • 継続学習モデルは、変化する交絡変数に対して不変な特徴表現を維持する上で課題に直面しています。

研究 の 目的:

  • 深層学習における交絡因子の影響を軽減するための新しいレイヤー、再帰的MDN（R-MDN）を開発すること。
  • 継続学習の設定において、交絡変数に対して不変な特徴表現を可能にすること。
  • 静的学習と継続学習の両方で、多様な集団グループ全体での予測公平性を向上させること。

主な方法:

  • 様々な深層学習アーキテクチャとステージに適応可能な再帰的MDN（R-MDN）レイヤーを導入しました。
  • モデルの内部状態を継続的に更新するために、統計的回帰に再帰的最小二乗法を採用しました。
  • 進化するデータと交絡変数の分布に基づいて特徴表現を調整するためにR-MDNを統合しました。

主要な成果:

  • R-MDNが、集団グループ全体で公平な予測を促進する上で効果的であることを実証しました。
  • R-MDNが、継続学習シナリオにおいて破滅的忘却を軽減する能力を示しました。
  • 変化する交絡因子を持つ静的および動的な学習環境の両方でR-MDNのパフォーマンスを検証しました。

結論:

  • R-MDNレイヤーは、深層学習、特に継続学習フレームワークにおける交絡変数の処理に堅牢なソリューションを提供します。
  • R-MDNは、交絡変数に対する特徴の不変性を保証することにより、モデルの公平性と堅牢性を向上させます。
  • このアプローチは、時間の経過とともにモデルのパフォーマンスと一般化に対する交絡因子の悪影響を軽減します。