Cargando…
Accurate, interpretable predictions of materials properties within transformer language models
Property prediction accuracy has long been a key parameter of machine learning in materials informatics. Accordingly, advanced models showing state-of-the-art performance turn into highly parameterized black boxes missing interpretability. Here, we present an elegant way to make their reasoning tran...
| Autores principales: | , |
|---|---|
| Formato: | Online Artículo Texto |
| Lenguaje: | English |
| Publicado: |
Elsevier
2023
|
| Materias: | |
| Acceso en línea: | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10591138/ https://www.ncbi.nlm.nih.gov/pubmed/37876904 http://dx.doi.org/10.1016/j.patter.2023.100803 |