Optical Scattering Characteristics of Three-Dimensional Targets Based on Transfer Learning PINNs
Renxian Li, Jiaze Huang, Huan Tang, Chenxu Zhou, Fengbei Liu, Zhe Wang · 2026
Read Optical Scattering Characteristics of Three-Dimensional Targets Based on Transfer Learning PINNs by Renxian Li, Jiaze Huang, Huan Tang, Chenxu Zhou, Fengbei Liu, Zhe Wang (2026) in the Tower of Babel, a free online library of public-domain works preserved in clean, searchable text. No sign-up. The full text is served as a plain-text file at a predictable URL, where text is present: https://antarctic-labs.com/tower-of-babel/pmc-13609419.txt.
Description
Renxian Li and co-authors speed up physics informed neural networks for light scattering from three dimensional targets in a 2026 paper. Such networks predict electromagnetic fields but train slowly, and retraining for each new shape or incoming field is costly.
Their framework embeds grid based Maxwell operators into the loss, so predicted fields obey the discrete equations directly. A layer freezing strategy keeps general wave knowledge learned earlier. New shapes or fields then need only fine tuning of a few task specific parameters. Tests show far fewer training rounds and lower retraining cost at similar accuracy.
Catalog record
| CREATOR | Renxian Li, Jiaze Huang, Huan Tang, Chenxu Zhou, Fengbei Liu, Zhe Wang |
|---|---|
| YEAR | 2026 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 59 KB |
| VERSION | 1.0 |
| LICENSE | CC BY 4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |