EUVIMEDEUVIMED entdecken
Crossref

Incommensurable Targets in Machine Learning for Nanomaterials: How Dose-Metric Heterogeneity Imposes an Irreducible Error Floor on Pooled Training Data

Igwe Emmanuel Sunday, UDEH Samuel Chibueze

IIAR Journal of Science, Engineering, and Applied Research · 27.10.2026 · 1 (1) · 37-46

DOI: 10.68854/n5jzte45 ↗

Kurz gefasst

Fachartikel in der Zeitschrift IIAR Journal of Science, Engineering, and Applied Research, online erschienen am 27.10.2026. Verfasst von Igwe Emmanuel Sunday und 1 weiteren Autor:innen.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Kein Abstract verfügbar.

Zitieren

APA

Sunday, I. E., & Chibueze, U. S. (2026). Incommensurable Targets in Machine Learning for Nanomaterials: How Dose-Metric Heterogeneity Imposes an Irreducible Error Floor on Pooled Training Data. IIAR Journal of Science, Engineering, and Applied Research, 1(1), 37-46. https://doi.org/10.68854/n5jzte45

Vancouver

Sunday IE, Chibueze US. Incommensurable Targets in Machine Learning for Nanomaterials: How Dose-Metric Heterogeneity Imposes an Irreducible Error Floor on Pooled Training Data. IIAR Journal of Science, Engineering, and Applied Research. 2026;1(1):37-46. doi:10.68854/n5jzte45

BibTeX
@article{Sunday2026,
  author = {Sunday, Igwe Emmanuel and Chibueze, UDEH Samuel},
  title = {Incommensurable Targets in Machine Learning for Nanomaterials: How Dose-Metric Heterogeneity Imposes an Irreducible Error Floor on Pooled Training Data},
  journal = {IIAR Journal of Science, Engineering, and Applied Research},
  year = {2026},
  volume = {1},
  number = {1},
  pages = {37--46},
  doi = {10.68854/n5jzte45}
}
Kostenlos starten →