Model editing for distribution shifts in uranium oxide morphological analysis
Zapisane w:
| Wydane w: | arXiv.org (Jul 22, 2024), p. n/a |
|---|---|
| 1. autor: | |
| Kolejni autorzy: | , , , , , |
| Wydane: |
Cornell University Library, arXiv.org
|
| Hasła przedmiotowe: | |
| Dostęp online: | Citation/Abstract Full text outside of ProQuest |
| Etykiety: |
Nie ma etykietki, Dołącz pierwszą etykiete!
|
MARC
| LEADER | 00000nab a2200000uu 4500 | ||
|---|---|---|---|
| 001 | 3083763541 | ||
| 003 | UK-CbPIL | ||
| 022 | |a 2331-8422 | ||
| 035 | |a 3083763541 | ||
| 045 | 0 | |b d20240722 | |
| 100 | 1 | |a Brown, Davis | |
| 245 | 1 | |a Model editing for distribution shifts in uranium oxide morphological analysis | |
| 260 | |b Cornell University Library, arXiv.org |c Jul 22, 2024 | ||
| 513 | |a Working Paper | ||
| 520 | 3 | |a Deep learning still struggles with certain kinds of scientific data. Notably, pretraining data may not provide coverage of relevant distribution shifts (e.g., shifts induced via the use of different measurement instruments). We consider deep learning models trained to classify the synthesis conditions of uranium ore concentrates (UOCs) and show that model editing is particularly effective for improving generalization to distribution shifts common in this domain. In particular, model editing outperforms finetuning on two curated datasets comprising of micrographs taken of U\(_{3}\)O\(_{8}\) aged in humidity chambers and micrographs acquired with different scanning electron microscopes, respectively. | |
| 653 | |a Uranium ores | ||
| 653 | |a Editing | ||
| 653 | |a Photomicrographs | ||
| 653 | |a Deep learning | ||
| 653 | |a Measuring instruments | ||
| 653 | |a Uranium oxides | ||
| 700 | 1 | |a Nizinski, Cody | |
| 700 | 1 | |a Shapiro, Madelyn | |
| 700 | 1 | |a Fallon, Corey | |
| 700 | 1 | |a Yin, Tianzhixi | |
| 700 | 1 | |a Kvinge, Henry | |
| 700 | 1 | |a Tu, Jonathan H | |
| 773 | 0 | |t arXiv.org |g (Jul 22, 2024), p. n/a | |
| 786 | 0 | |d ProQuest |t Engineering Database | |
| 856 | 4 | 1 | |3 Citation/Abstract |u https://www.proquest.com/docview/3083763541/abstract/embedded/75I98GEZK8WCJMPQ?source=fedsrch |
| 856 | 4 | 0 | |3 Full text outside of ProQuest |u http://arxiv.org/abs/2407.15756 |