Feature Mapping in Physics-Informed Neural Networks (PINNs)
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2024
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866917809320099840 |
|---|---|
| author | Zeng, Chengxi Burghardt, Tilo Gambaruto, Alberto M |
| author_facet | Zeng, Chengxi Burghardt, Tilo Gambaruto, Alberto M |
| contents | In this paper, the training dynamics of PINNs with a feature mapping layer via the limiting Conjugate Kernel and Neural Tangent Kernel is investigated, shedding light on the convergence of PINNs; Although the commonly used Fourier-based feature mapping has achieved great success, we show its inadequacy in some physics scenarios. Via these two scopes, we propose conditionally positive definite Radial Basis Function as a better alternative. Lastly, we explore the feature mapping numerically in wide neural networks. Our empirical results reveal the efficacy of our method in diverse forward and inverse problem sets. Composing feature functions is found to be a practical way to address the expressivity and generalisability trade-off, viz., tuning the bandwidth of the kernels and the surjectivity of the feature mapping function. This simple technique can be implemented for coordinate inputs and benefits the broader PINNs research. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2402_06955 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Feature Mapping in Physics-Informed Neural Networks (PINNs) Zeng, Chengxi Burghardt, Tilo Gambaruto, Alberto M Machine Learning Artificial Intelligence Computational Engineering, Finance, and Science In this paper, the training dynamics of PINNs with a feature mapping layer via the limiting Conjugate Kernel and Neural Tangent Kernel is investigated, shedding light on the convergence of PINNs; Although the commonly used Fourier-based feature mapping has achieved great success, we show its inadequacy in some physics scenarios. Via these two scopes, we propose conditionally positive definite Radial Basis Function as a better alternative. Lastly, we explore the feature mapping numerically in wide neural networks. Our empirical results reveal the efficacy of our method in diverse forward and inverse problem sets. Composing feature functions is found to be a practical way to address the expressivity and generalisability trade-off, viz., tuning the bandwidth of the kernels and the surjectivity of the feature mapping function. This simple technique can be implemented for coordinate inputs and benefits the broader PINNs research. |
| title | Feature Mapping in Physics-Informed Neural Networks (PINNs) |
| topic | Machine Learning Artificial Intelligence Computational Engineering, Finance, and Science |
| url | https://arxiv.org/abs/2402.06955 |