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

Phase Transitions02:31

Phase Transitions

20.2K
Whether solid, liquid, or gas, a substance's state depends on the order and arrangement of its particles (atoms, molecules, or ions). Particles in the solid pack closely together, generally in a pattern. The particles vibrate about their fixed positions but do not move or squeeze past their neighbors. In liquids, although the particles are closely spaced, they are randomly arranged. The position of the particles are not fixed—that is, they are free to move past their neighbors to...
20.2K
Phase Transitions: Sublimation and Deposition02:33

Phase Transitions: Sublimation and Deposition

17.9K
Some solids can transition directly into the gaseous state, bypassing the liquid state, via a process known as sublimation. At room temperature and standard pressure, a piece of dry ice (solid CO2) sublimes, appearing to gradually disappear without ever forming any liquid. Snow and ice sublimate at temperatures below the melting point of water, a slow process that may be accelerated by winds and the reduced atmospheric pressures at high altitudes. When solid iodine is warmed, the solid sublimes...
17.9K
Phase Changes01:19

Phase Changes

4.5K
Phase transitions play an important theoretical and practical role in the study of heat flow. In melting or fusion, a solid turns into a liquid; the opposite process is freezing. In evaporation, a liquid turns into a gas; the opposite process is condensation.
A substance melts or freezes at a temperature called its melting point and boils or condenses at its boiling point. These temperatures depend on pressure. High pressure favors the denser form of the substance, so typically, high pressure...
4.5K
Dynamic Equilibrium02:20

Dynamic Equilibrium

53.3K
A reversible chemical reaction represents a chemical process that proceeds in both forward (left to right) and reverse (right to left) directions. When the rates of the forward and reverse reactions are equal, the concentrations of the reactant and product species remain constant over time and the system is at equilibrium. A special double arrow is used to emphasize the reversible nature of the reaction. The relative concentrations of reactants and products in equilibrium systems vary greatly;...
53.3K
Generalization, Discrimination, and Extinction01:24

Generalization, Discrimination, and Extinction

784
Generalization, discrimination, and extinction are key concepts in operant conditioning that influence how behaviors are learned and maintained.
Generalization occurs when a behavior reinforced in one context is performed in similar situations. For instance, a student who studies diligently for calculus and receives excellent grades might apply the same study habits to psychology and history, expecting similar results. Generalization shows how learning in one setting can influence behavior in...
784
Phase Diagram01:19

Phase Diagram

6.1K
The phase of a given substance depends on the pressure and temperature. Thus, plots of pressure versus temperature showing the phase in each region provide considerable insights into the thermal properties of substances. Such plots are known as phase diagrams. For instance, in the phase diagram for water (Figure 1), the solid curve boundaries between the phases indicate phase transitions (i.e., temperatures and pressures at which the phases coexist).
6.1K

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

From PINNs to PIKANs: recent advances in physics-informed machine learning.

Machine learning for computational science and engineering·2026
Same author

Automatic selection of the best neural architecture for time series forecasting.

Nature communications·2026
Same author

First-in-human implantation of a self-adjustable glaucoma drainage device (eyeValve): safety and performance in blind eyes.

Graefe's archive for clinical and experimental ophthalmology = Albrecht von Graefes Archiv fur klinische und experimentelle Ophthalmologie·2026
Same author

MR-AIV reveals in vivo brain-wide fluid flow with physics-informed AI.

Science advances·2026
Same author

An AI-enabled tool for quantifying overlapping red blood cell sickling dynamics in microfluidic assays.

Lab on a chip·2026
Same author

A Multiscale Signaling-Biophysical Framework Reveals Mechanisms of Macrophage-Mediated RBC Clearance in Sickle Cell and Gaucher Disease.

bioRxiv : the preprint server for biology·2026
Same journal

A boundary-regularization-enhanced video anomaly detection network based on context-adaptive spatio-temporal conditional diffusion.

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

MT<sup>2</sup>-CSD and LLM-CRAN: A new dataset and an LLM-based multi-semantic knowledge fusion model for conversational stance detection.

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

TriAlignNet: A triple-path cross-modality alignment framework for multimodal time series forecasting.

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

Anchor-based disentanglement framework for incremental multi-view clustering.

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

Complex-valued amplitude-phase interference modeling for adversarially robust classification.

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

TraNce: Type-aware hypergraph neural network with biological mediators for drug repositioning.

Neural networks : the official journal of the International Neural Network Society·2026
関連記事をすべて見る

関連する実験動画

Updated: Sep 9, 2025

Phase Diagram Characterization Using Magnetic Beads as Liquid Carriers
12:37

Phase Diagram Characterization Using Magnetic Beads as Liquid Carriers

Published on: September 4, 2015

12.5K

PINNでの学習:フェーズ移行,拡散均衡,および一般化

Sokratis J Anagnostopoulos1, Juan Diego Toscano2, Nikolaos Stergiopulos1

  • 1Laboratory of Hemodynamics and Cardiovascular Technology, EPFL, Lausanne, 1015, VD, Switzerland.

Neural networks : the official journal of the International Neural Network Society
|August 30, 2025
PubMed
まとめ
この要約は機械生成です。

ニューラルネットワークの訓練において グラデーションが並べられ 安定した収束に至る 新しい"拡散均衡"の段階を 特定しました この段階は,均質な残量と組み合わせると,モデルの一般化を促進し,学習を加速します.

キーワード:
一般化グラデーションストキャスティシティ情報ボトルネック理論PINNsのフェーズ移行残った均質性

さらに関連する動画

Slice Patch Clamp Technique for Analyzing Learning-Induced Plasticity
11:56

Slice Patch Clamp Technique for Analyzing Learning-Induced Plasticity

Published on: November 11, 2017

15.6K
Phase Behavior of Charged Vesicles Under Symmetric and Asymmetric Solution Conditions Monitored with Fluorescence Microscopy
10:08

Phase Behavior of Charged Vesicles Under Symmetric and Asymmetric Solution Conditions Monitored with Fluorescence Microscopy

Published on: October 24, 2017

9.3K

関連する実験動画

Last Updated: Sep 9, 2025

Phase Diagram Characterization Using Magnetic Beads as Liquid Carriers
12:37

Phase Diagram Characterization Using Magnetic Beads as Liquid Carriers

Published on: September 4, 2015

12.5K
Slice Patch Clamp Technique for Analyzing Learning-Induced Plasticity
11:56

Slice Patch Clamp Technique for Analyzing Learning-Induced Plasticity

Published on: November 11, 2017

15.6K
Phase Behavior of Charged Vesicles Under Symmetric and Asymmetric Solution Conditions Monitored with Fluorescence Microscopy
10:08

Phase Behavior of Charged Vesicles Under Symmetric and Asymmetric Solution Conditions Monitored with Fluorescence Microscopy

Published on: October 24, 2017

9.3K

科学分野:

  • ディープラーニングの最適化
  • 神経ネットワークのダイナミクス
  • 機械学習理論

背景:

  • ニューラルネットワークの学習ダイナミクスを理解することは,モデルのパフォーマンスを改善するために不可欠です.
  • 既存の理論は,訓練におけるドリフトと拡散の段階を記述しています.
  • これらの段階におけるグラデント信号対ノイズ比 (SNR) の役割については,さらなる調査が必要である.

研究 の 目的:

  • グラデントSNRを用いた完全に接続されたニューラルネットワークの学習ダイナミクスを調査する.
  • 漂流と拡散を超えた新しい訓練段階を特定し,特徴づけること.
  • 観察されたダイナミクスに基づいて一般化と収束を改善するための方法を提案する.

主な方法:

  • 非凸なオブジェクトのファーストオーダー最適化器の分析.
  • 情報のボトルネック理論のレンズを通してトレーニングの段階の解釈.
  • 神経グラデーションの信号対ノイズ比 (SNR) の検査
  • 試料別重量化システムの開発と試験

主要な成果:

  • 新作の識別
  • 拡散均衡
  • 秩序ある神経グラデントと安定した収束によって特徴づけられる.
  • DE相は,増加したSNRと均質な残留値と相関し,よりよい一般化につながります.
  • 提案されたサンプル別再重量化スキームは,残留の均一性と一般化を改善します.
  • 飽和誘導によるDE相移行中の活性化圧縮の観測
  • 物理情報に基づくニューラルネットワーク (PINNs) の実験的検証により,より迅速な収束と一般化が示されました.

結論:

  • 特定されたDE段階は,安定したニューラルネットワークの訓練に関する新しい視点を提供します.
  • DE段階では,順番のグラデントに沿って均質な残留値を達成することは,優れた一般化のための鍵です.
  • この発見は,特に物理学に基づいた最適化戦略の改善の可能性を示唆しています.