Cargando…
A universal similarity based approach for predictive uncertainty quantification in materials science
Immense effort has been exerted in the materials informatics community towards enhancing the accuracy of machine learning (ML) models; however, the uncertainty quantification (UQ) of state-of-the-art algorithms also demands further development. Most prominent UQ methods are model-specific or are rel...
Autores principales: | Korolev, Vadim, Nevolin, Iurii, Protsenko, Pavel |
---|---|
Formato: | Online Artículo Texto |
Lenguaje: | English |
Publicado: |
Nature Publishing Group UK
2022
|
Materias: | |
Acceso en línea: | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9440040/ https://www.ncbi.nlm.nih.gov/pubmed/36056050 http://dx.doi.org/10.1038/s41598-022-19205-5 |
Ejemplares similares
-
Accurate, interpretable predictions of materials properties within transformer language models
por: Korolev, Vadim, et al.
Publicado: (2023) -
Laboratory-based X-ray spectrometer for actinide science
por: Novichkov, Daniil, et al.
Publicado: (2023) -
Uncertainty quantification and predictive computational science: a foundation for physical scientists and engineers
por: McClarren, Ryan G
Publicado: (2018) -
Similarity-based pairing improves efficiency of siamese neural networks for regression tasks and uncertainty quantification
por: Zhang, Yumeng, et al.
Publicado: (2023) -
Uncertainty Quantification of Material Properties in Ballistic Impact of Magnesium Alloys
por: Sun, Xingsheng
Publicado: (2022)