関連する実験動画
Updated: Sep 9, 2025
13:19
Deep Neural Networks for Image-Based Dietary Assessment
Published on: March 13, 2021
9.3K
極端な不連続性を持つ高次元の微分逆の問題のための情報蒸留物理学による深層学習
Mingsheng Peng1,2, Hesheng Tang3,4
1Department of Disaster Mitigation for Structures, College of Civil Engineering, Tongji University, Shanghai, China.
Communications engineering
|September 1, 2025
まとめ
この研究は,鋭い不連続性を持つ複雑な逆の問題に取り組むために,高度な物理情報に基づいたディープラーニングの枠組みを導入します. この新しいアプローチは,誤った情報を効果的に抑制し,局所的な変化でも正確性を確保します.
科学分野:
- コンピュータ科学
- 人工知能
- 応用数学
背景:
- 標準的な物理情報に基づいたディープラーニングは,極端な不連続性と高次元のパラメータ化された微分方程式を含む逆の問題と闘っています.
- ディープラーニングモデルのグローバル・スムーズ・アクティベーション関数は,パラメータが空間的に分散したり,急激に変化したりすると,不適切なグラデーションにつながります.
研究 の 目的:
- 重度の不連続性を持つ逆問題を正確に解くことができる新しい物理情報に基づいたディープラーニングの枠組みを開発する.
- シングルリティと悪質なグラデントフローの処理における既存の方法の限界に対処する.
主な方法:
- 提案されたフレームワークは,縮小型モデリング,多レベルドメイン分解,および悪質コンディショニング抑制メカニズムを統合しています.
- 不良条件のグラデント情報を管理するために,情報伝播と蒸留戦略を使用します.
- このアプローチは,局所的な領域における不連続性によって引き起こされる急速な変数変化を捉えるように設計されています.
主要な成果:
- このフレームワークは,断続性によって引き起こされる高度に局所化された地域内の変数の急速な変動をうまく捉えています.
- システムのグラデントフローに欠陥のある情報は,情報伝播と蒸留によって効果的に抑制されます.
- このフレームワークは,一部のサブネットワークが故障した場合でも,ほとんどのサブネットワークで精度を維持します.
結論:
- 開発された情報蒸留物理情報に基づくディープラーニングフレームワークは,極端な不連続性を持つ逆の問題に堅実な解決策を提供します.
- この新しいアプローチにより 複雑な科学技術アプリケーションにおける ディープラーニングモデルの安定性と正確性が向上します
- この方法は,ネットワーク内の局所的な故障にもかかわらず,レジリエンスを示し,予測力を維持します.
関連する概念動画
01:22Second Derivatives and Laplace Operator
1.5K
The first order operators using the del operator include the gradient, divergence and curl. Certain combinations of first order operators on a scalar or vector function yield second order expressions. Second-order expressions play a very important role in mathematics and physics. Some second order expressions include the divergence and curl of a gradient function, the divergence and curl of a curl function, and the gradient of a divergence function.
Consider a scalar function. The curl of its...
Consider a scalar function. The curl of its...
1.5K
01:17Differential Form of Maxwell's Equations
636
James Clerk Maxwell (1831–1879) was one of the significant contributors to physics in the nineteenth century. He is probably best known for having combined existing knowledge of the laws of electricity and the laws of magnetism with his insights to form a complete overarching electromagnetic theory, represented by Maxwell's equations. The four basic laws of electricity and magnetism were discovered experimentally through the work of physicists such as Oersted, Coulomb, Gauss, and...
636
01:06Divergence and Stokes' Theorems
1.9K
The divergence and Stokes' theorems are a variation of Green's theorem in a higher dimension. They are also a generalization of the fundamental theorem of calculus. The divergence theorem and Stokes' theorem are in a way similar to each other; The divergence theorem relates to the dot product of a vector, while Stokes' theorem relates to the curl of a vector. Many applications in physics and engineering make use of the divergence and Stokes' theorems, enabling us to write...
1.9K
01:18Uniform Depth Channel Flow: Problem Solving
124
To calculate the flow rate for a trapezoidal channel, first, identify the bottom width, side slope, and flow depth of the channel. The cross-sectional area (A) corresponding to the depth of flow (y), channel bottom width (B), and side slope (θ) is determined by:Next, calculate the wetted perimeter, which includes the bottom width and the sloped side lengths in contact with the water. Using the values of the cross-sectional area and the wetted perimeter, determine the hydraulic radius by...
124
01:24Convolution: Math, Graphics, and Discrete Signals
396
In any LTI (Linear Time-Invariant) system, the convolution of two signals is denoted using a convolution operator, assuming all initial conditions are zero. The convolution integral can be divided into two parts: the zero-input or natural response and the zero-state or forced response, with t0 indicating the initial time.
To simplify the convolution integral, it is assumed that both the input signal and impulse response are zero for negative time values. The graphical convolution process...
To simplify the convolution integral, it is assumed that both the input signal and impulse response are zero for negative time values. The graphical convolution process...
396
01:26Transmission-Line Differential Equations
401
Transmission lines are essential components of electrical power systems. They are characterized by the distributed nature of resistance (R), inductance (L), and capacitance (C) per unit length. To analyze these lines, differential equations are employed to model the variations in voltage and current along the line.
Line Section Model
A circuit representing a line section of length Δx helps in understanding the transmission line parameters. The voltage V(x) and current i(x) are measured...
Line Section Model
A circuit representing a line section of length Δx helps in understanding the transmission line parameters. The voltage V(x) and current i(x) are measured...
401