A comparison of explainable artificial intelligence methods in the phase classification of multi-principal element alloys

We demonstrate the capabilities of two model-agnostic local post-hoc model interpretability methods, namely breakDown (BD) and shapley (SHAP), to explain the predictions of a black-box classification learning model that establishes a quantitative relationship between chemical composition and multi-p...

Descripción completa

Detalles Bibliográficos
Autores principales: Lee, Kyungtae, Ayyasamy, Mukil V., Ji, Yangfeng, Balachandran, Prasanna V.
Formato: Online Artículo Texto
Lenguaje:English
Publicado: Nature Publishing Group UK 2022
Materias:
Article
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9270422/
https://www.ncbi.nlm.nih.gov/pubmed/35804179
http://dx.doi.org/10.1038/s41598-022-15618-4

Internet

https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9270422/
https://www.ncbi.nlm.nih.gov/pubmed/35804179
http://dx.doi.org/10.1038/s41598-022-15618-4

Ejemplares similares