Metraipolis › archive › dc_56e4e2b2f8e8

PRISM-UDE: Physics-Regularized Iterative Symbolic Modeling of 3nm FinFETs via Universal Differential Equation — arXiv:2609.13200

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.13200
License (as archived)
CC0-1.0
Archived
2026-10-16T00:12:14.931Z
SHA-256 of the archived text
29661a13491d6795bb964d383ec43eb0fa8df2f76797e374d910bf6a705b9019
Stable URL of this page
https://metraipolis.com/documento/dc_56e4e2b2f8e8

How to cite

PRISM-UDE: Physics-Regularized Iterative Symbolic Modeling of 3nm FinFETs via Universal Differential Equation — arXiv:2609.13200 — arXiv (en), https://arxiv.org/abs/2609.13200 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_56e4e2b2f8e8 (Metraipolis archive dc_56e4e2b2f8e8, sha256 29661a13491d6795bb964d383ec43eb0fa8df2f76797e374d910bf6a705b9019)
BibTeX
@misc{dc56e4e2b2f8e8,
  title = {PRISM-UDE: Physics-Regularized Iterative Symbolic Modeling of 3nm FinFETs via Universal Differential Equation — arXiv:2609.13200},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.13200},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_56e4e2b2f8e8; sha256 29661a13491d6795bb964d383ec43eb0fa8df2f76797e374d910bf6a705b9019},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.13200. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Compact transistor models are the mathematical backbone of circuit simulation. However, at advanced nodes such as 3nm, transport physics becomes too complex for traditional hand-derived equations to capture accurately. Purely data-driven neural surrogates, on the other hand, are numerically unstable inside circuit solvers and offer no physical insight into their own predictions. We introduce PRISM-UDE (Physics-Regularized Iterative Symbolic Modeling via Universal Differential Equations), a framework that embeds a small neural network inside a physics-based transistor model, using the network only to learn the transport behavior that the analytical baseline misses, rather than replacing the physics altogether. Once trained, this neural correction is distilled into a single, interpretable closed-form expression via symbolic regression, making the final model fully analytical and simulator-ready. Applied to a 3nm FinFET benchmark dataset, PRISM-UDE reduces prediction error more than sixfold (70.33% to 11.01%) relative to the standard physics-only baseline. The distilled expression preserves this accuracy almost exactly while eliminating the neural network entirely. We further validate the extracted expression directly inside a SPICE circuit simulator, confirming stable, physically consistent behavior under both static bias sweeps and dynamic switching conditions.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-15 in cs.LG).
Categorie arXiv: Emerging Technologies (cs.ET) ; Machine Learning (cs.LG).
Pagina del lavoro: https://arxiv.org/abs/2609.13200 — 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 2026-10-15T23:54:14.812Z dalla pagina https://arxiv.org/catchup/cs.LG/2026-09-15?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).