Imagen de Portada

Model editing for distribution shifts in uranium oxide morphological analysis

Guardado en:
Publicado en:arXiv.org (Jul 22, 2024), p. n/a
Autor principal: Brown, Davis
Otros Autores: Nizinski, Cody, Shapiro, Madelyn, Fallon, Corey, Yin, Tianzhixi, Kvinge, Henry, Tu, Jonathan H
Publicado:
Cornell University Library, arXiv.org
Materias:
Uranium ores
Editing
Photomicrographs
Deep learning
Measuring instruments
Uranium oxides
Acceso en línea:Citation/Abstract
Full text outside of ProQuest
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
Resumen: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.
ISSN:2331-8422
Fuente:Engineering Database