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

PID Controller01:19

PID Controller

742
Proportional-Integral-Derivative (PID) controllers are widely used in various control systems to enhance stability and performance. In a thermostat, it adjusts heating or cooling based on the temperature difference between the actual and desired levels. They are often used in automotive speed systems, effectively managing sudden speed changes while maintaining a constant speed under varying conditions. On the other hand, PI controllers, commonly employed in voltage regulation, enhance stability...
742
Avoidance Learning and Learned Helplessness01:14

Avoidance Learning and Learned Helplessness

2.6K
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...
2.6K
Layers of the Epidermis01:21

Layers of the Epidermis

8.8K
The epidermis, the outermost layer of the skin, is composed of several distinct layers. From deep to superficial, the layers of the epidermis are as follows:
Stratum Basale
Stratum basale, also known as the stratum germinativum, is the deepest layer of the epidermis. It is composed of a single layer of actively dividing cells called basal cells or basal keratinocytes. These cells constantly undergo cell division to replenish the upper layers of the epidermis. Additionally, melanocytes, which...
8.8K
Combinatorial Gene Control02:33

Combinatorial Gene Control

9.7K
Combinatorial gene control is the synergistic action of several transcriptional factors to regulate the expression of a single gene. The absence of one or more of these factors may lead to a significant difference in the level of gene expression or repression.
The expression of more than 30,000 genes is controlled by approximately 2000-3000 transcription factors. This is possible because a single transcription factor can recognize more than one regulatory sequence. The specificity in gene...
9.7K
Associative Learning01:27

Associative Learning

1.5K
Associative learning is a fundamental concept in behavioral psychology, wherein a connection is established between two stimuli or events, leading to a learned response. This process is critical in understanding how behaviors are acquired and modified. Conditioning, the mechanism through which associations are formed, can be divided into two main types: classical conditioning and operant conditioning, each elucidating different aspects of associative learning.
Classical conditioning, also known...
1.5K
Purposive Learning01:22

Purposive Learning

518
E. C. Tolman emphasized the purposiveness of behavior — the idea that much of our behavior is goal-directed. For instance, employees who aim for a promotion work diligently to meet their targets. Tolman argued that when classical conditioning and operant conditioning occur, the organism acquires certain expectations. In classical conditioning, a child might fear a dog because they expect it to bite. In operant conditioning, a person might consistently work overtime because they expect a...
518

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

Functionalized carbon nanotube-assisted dual-mode CRISPR/Cas12a detection of hepatitis C virus via catalytic assembly circuit-driven Y-shaped dsDNA activators.

Biosensors & bioelectronics·2026
Same author

An Electrical Capacitance Tomography Dataset for Image Reconstruction Benchmarking.

Scientific data·2026
Same author

Proactive collaboration via autonomous interaction.

Nature communications·2026
Same author

DynamicTHOR: A Scalable Dataset of Human-Centric Dynamic Scenes for Embodied AI.

Scientific data·2026
Same author

S2R-Bench: A Sim-to-Real Evaluation Benchmark for Autonomous Driving.

Scientific data·2025
Same author

A Visual Dataset for Anomaly Detection in Self-Driving Laboratories.

Scientific data·2025
Same journal

Benchmarking the Robustness of Autonomous Driving to Environmental Illusions: A Lane Perception Perspective.

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

Learning Topology-Aware Representations via Test-Time Adaptation for Anomaly Segmentation.

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

TraGraph-GS: Trajectory Graph-based Gaussian Splatting for Arbitrary Large-Scale Scene Rendering.

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

SWIFT: A Small-World Interaction Framework for Flow-Aware Trajectory Prediction in Autonomous Driving.

IEEE transactions on pattern analysis and machine intelligence·2026
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
関連記事をすべて見る

関連する実験動画

Updated: Feb 13, 2026

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

11.2K

層適応型PID制御による少数ショットタスクにおける学習効率の向上

Pengfei Zhang, Xinde Li, Le Yu

    IEEE transactions on pattern analysis and machine intelligence
    |February 11, 2026
    PubMed
    まとめ
    この要約は機械生成です。

    本研究では、少数ショット学習を改善するための層適応型比例積分微分（LA-PID）オプティマイザーを導入する。この新しいアプローチは、モデルの適応を強化し、少数ショット分類およびドメイン間タスクにおいて最先端の結果を達成する。

    キーワード:
    少数ショット学習メタ学習適応PID制御機械学習

    さらに関連する動画

    The 5-Choice Serial Reaction Time Task: A Task of Attention and Impulse Control for Rodents
    09:43

    The 5-Choice Serial Reaction Time Task: A Task of Attention and Impulse Control for Rodents

    Published on: August 10, 2014

    47.0K
    Utilizing Electroencephalography Measurements for Comparison of Task-Specific Neural Efficiencies: Spatial Intelligence Tasks
    06:57

    Utilizing Electroencephalography Measurements for Comparison of Task-Specific Neural Efficiencies: Spatial Intelligence Tasks

    Published on: August 9, 2016

    11.9K

    関連する実験動画

    Last Updated: Feb 13, 2026

    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

    11.2K
    The 5-Choice Serial Reaction Time Task: A Task of Attention and Impulse Control for Rodents
    09:43

    The 5-Choice Serial Reaction Time Task: A Task of Attention and Impulse Control for Rodents

    Published on: August 10, 2014

    47.0K
    Utilizing Electroencephalography Measurements for Comparison of Task-Specific Neural Efficiencies: Spatial Intelligence Tasks
    06:57

    Utilizing Electroencephalography Measurements for Comparison of Task-Specific Neural Efficiencies: Spatial Intelligence Tasks

    Published on: August 9, 2016

    11.9K

    科学分野:

    • 機械学習
    • 人工知能
    • 制御理論

    背景:

    • 少数ショット学習は、最小限のデータで新しいカテゴリを分類することを目指しています。
    • モデルに依存しないメタ学習（MAML）は、迅速な適応のための柔軟な初期化を提供します。
    • MAMLは、大幅な分布シフトに対処するのに苦労し、一般化と効率的な学習を妨げます。

    研究 の 目的:

    • 分布シフトの処理におけるMAMLの限界に対処すること。
    • 初期化を超えたメタ学習における適応プロセスを強化すること。
    • さまざまなタスクにおける少数ショット学習パフォーマンスを向上させること。

    主な方法:

    • 新しい層適応型比例積分微分（LA-PID）オプティマイザーを提案しました。
    • LA-PIDをメタ学習フレームワークに統合しました。
    • 古典制御理論（PID制御）の原理を適用して、ネットワーク層のゲインを動的に調整しました。

    主要な成果:

    • 少数ショット分類ベンチマークで最先端のパフォーマンスを達成しました。
    • ドメイン間少数ショット学習タスクで優れた結果を示しました。
    • より少ないトレーニングステップで少数ショット回帰タスクにおける有効性を示しました。

    結論:

    • LA-PIDは、メタ学習における適応能力を大幅に向上させます。
    • 提案手法は、分布シフトにおけるMAMLの限界を克服します。
    • LA-PIDは、データ不足の学習シナリオに対して、堅牢で効率的なソリューションを提供します。