Metraipolis › archive › dc_a3fd9a170eed

An improved periodic activation for PINNs reconstructing convective flows — arXiv:2609.21798

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.21798
License (as archived)
CC0-1.0
Archived
2026-10-08T10:57:46.358Z
SHA-256 of the archived text
b7e8d043198157b48870b0a8aed98101705364aabec532b1293e920b0c3fcfe7
Stable URL of this page
https://metraipolis.com/documento/dc_a3fd9a170eed

How to cite

An improved periodic activation for PINNs reconstructing convective flows — arXiv:2609.21798 — arXiv (en), https://arxiv.org/abs/2609.21798 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_a3fd9a170eed (Metraipolis archive dc_a3fd9a170eed, sha256 b7e8d043198157b48870b0a8aed98101705364aabec532b1293e920b0c3fcfe7)
BibTeX
@misc{dca3fd9a170eed,
  title = {An improved periodic activation for PINNs reconstructing convective flows — arXiv:2609.21798},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.21798},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_a3fd9a170eed; sha256 b7e8d043198157b48870b0a8aed98101705364aabec532b1293e920b0c3fcfe7},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.21798. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Architectures with periodic activation functions have already been shown to be beneficial in comparison to monotonic counterparts for a wide range of applications of physics-informed neural networks. Here, we investigate a network architecture which uses the complex exponential function, generating pairs of sine and cosine outputs as activation functions. Testing it against comparable, sine-activated multi-layer perceptrons for the task of temperature reconstruction from sparse velocity data for cubic Rayleigh-Bénard convection reveals significant improvements in the reconstruction quality without a substantial increase in computational cost per training step. Vice versa, the improved architecture enables reaching similar reconstruction qualities for a fraction of the expense. Analyzing the mathematical structure of these networks points to the improvements being rooted in the property of passing both a sine and cosine function forward. This way, the subsequent layer is able to adapt the phase of the provided latent periodic functions, and doing it individually for each of its neurons.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-24 in cs.LG).
Categorie arXiv: Fluid Dynamics (physics.flu-dyn) ; Machine Learning (cs.LG).
Pagina del lavoro: https://arxiv.org/abs/2609.21798 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-10-08T10:06:16.788Z dalla pagina https://arxiv.org/catchup/cs.LG/2026-09-24?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).