Cargando…
A structural characterization of shortcut features for prediction
With the rising use of machine learning for healthcare applications, practitioners are increasingly confronted with the limitations of prediction models that are trained in one setting but meant to be deployed in several others. One recently identified limitation is so-called shortcut learning, wher...
| Autores principales: | , , |
|---|---|
| Formato: | Online Artículo Texto |
| Lenguaje: | English |
| Publicado: |
Springer Netherlands
2022
|
| Materias: | |
| Acceso en línea: | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9256901/ https://www.ncbi.nlm.nih.gov/pubmed/35792990 http://dx.doi.org/10.1007/s10654-022-00892-3 |