物理システムの高周波スケーリングによるニューラルオペレータのスペクトルバイアスの軽減
Siavash Khodakarami1, Vivek Oommen2, Aniruddha Bora1
1Division of Applied Mathematics, Brown University, Providence, RI, 02912, USA.
まとめ
高周波スケーリング (HFS) は,複雑な物理モデリングのためのニューラルオペレータのスペクトルバイアスを軽減します. このアプローチは,フーリエ変換コストなしで流体フローシミュレーションの予測精度を高めます.
科学分野:
- 計算式流体力学
- 物理学の機械学習
- 科学的なモデリングのためのディープラーニング
背景:
- 神経オペレーターは 複雑な物理システムをモデル化するための 強力なツールです
- ニューラルオペレータのスペクトルバイアスは 高周波モードを捕捉する能力を制限し,スムーズな解決策につながります.
- 乱流や多相流のような多スケールシステムではこの制限が特に問題です.
研究 の 目的:
- 高周波スケーリング (HFS) という新しい方法を導入し,評価し,コンボリューションニューラルオペレータのスペクトルバイアスを軽減する.
- ニューラルオペレータの予測精度を向上させ,単相および二相フロー問題をモデリングする.
- 拡散モデルを使用して代替スペクトルバイアスの緩和戦略を探求する.
主な方法:
- 高周波スケーリング (HFS) をコンボリューションニューラルオペレータ,特にUNetの変種に開発し統合した.
- フーリエ変換の計算を避け,HFSを潜在空間に直接適用した.
- 標準版とHFS強化版を比較して,ニューラルオペレータに条件付けられた拡散モデルの使用を調査した.
主要な成果:
- HFSの統合は,スペクトルバイアスを軽減することにより,単相および二相フローの問題における予測精度を大幅に改善しました.
- HFSの方法は,フーリエベースのテクニックの計算上のオーバーヘッドなしで有効性を証明しました.
- HFS強化ニューラルオペレータと組み合わせた拡散モデルでは,標準ニューラルオペレータと比較してエラーが大幅に減少しました.
結論:
- 高周波スケーリング (HFS) は,収束神経オペレータにおけるスペクトルバイアスの対処のための効果的な技術である.
- HFSは,流体力学におけるニューラルオペレータのパフォーマンスを改善するために,フーリエベースの方法の計算効率の良い代替案を提供します.
- HFSと拡散モデルを組み合わせることで,複雑なフローシミュレーションのための物理情報に基づく機械学習モデルの精度がさらに向上します.
関連する概念動画
01:26Scaling
313
In designing and analyzing filters, resonant circuits, or circuit analysis at large, working with standard element values like 1 ohm, 1 henry, or 1 farad can be convenient before scaling these values to more realistic figures. This approach is widely utilized by not employing realistic element values in numerous examples and problems; it simplifies mastering circuit analysis through convenient component values. The complexity of calculations is thereby reduced, with the understanding that...
313
01:18Aliasing
224
Accurate signal sampling and reconstruction are crucial in various signal-processing applications. A time-domain signal's spectrum can be revealed using its Fourier transform. When this signal is sampled at a specific frequency, it results in multiple scaled replicas of the original spectrum in the frequency domain. The spacing of these replicas is determined by the sampling frequency.
If the sampling frequency is below the Nyquist rate, these replicas overlap, preventing the original...
If the sampling frequency is below the Nyquist rate, these replicas overlap, preventing the original...
224
01:22Upsampling
309
Managing signal sampling rates is essential in digital signal processing to maintain signal integrity. A decimated signal, characterized by a reduced frequency range due to its lower sampling rate, can be upsampled by inserting zeros between each sample. This upsampling process expands the original spectrum and introduces repeated spectral replicas at intervals dictated by the new Nyquist frequency. To refine this zero-inserted sequence, it is passed through a lowpass filter with a cutoff...
309
01:21Properties of Fourier series II
262
Time scaling of signals is a crucial concept in signal processing that affects the Fourier series representation without altering its coefficients. The process modifies the fundamental frequency, thereby changing how the series represents the signal over time. This principle is essential in various applications, including audio and image processing, where signal manipulation is frequent. Understanding function symmetries is fundamental to simplifying the Fourier series.
A function f(t) is...
A function f(t) is...
262
01:02¹H NMR: Interpreting Distorted and Overlapping Signals
1.1K
Spin systems where the difference in chemical shifts of the coupled nuclei is greater than ten times J are called first-order spin systems. These nuclei are weakly coupled, and their chemical shifts and coupling constant can generally be estimated from the well-separated signals in the spectrum.
As Δν decreases and the signals move closer, the doublets appear increasingly distorted. The intensities of the inner lines increase at the cost of those of the outer lines as the signals are...
As Δν decreases and the signals move closer, the doublets appear increasingly distorted. The intensities of the inner lines increase at the cost of those of the outer lines as the signals are...
1.1K
01:26Linear Approximation in Frequency Domain
131
Linear systems are characterized by two main properties: superposition and homogeneity. Superposition allows the response to multiple inputs to be the sum of the responses to each individual input. Homogeneity ensures that scaling an input by a scalar results in the response being scaled by the same scalar.
In contrast, nonlinear systems do not inherently possess these properties. However, for small deviations around an operating point, a nonlinear system can often be approximated as linear....
In contrast, nonlinear systems do not inherently possess these properties. However, for small deviations around an operating point, a nonlinear system can often be approximated as linear....
131