Nam++: achieving interpretability and fairness without sacrificing accuracy through neural additive models with selective feature interactions
Abstract Machine learning is everywhere now-lending, criminal justice, healthcare-and with that comes a real problem: transparency and fairness. Deep learning models can be powerful, but they are also black boxes. People affected by these decisions have no clear understanding of how they are being j...
Gorde:
| Egile nagusia: | |
|---|---|
| Formatua: | Artigo |
| Hizkuntza: | Inglês |
| Argitaratua: |
SpringerOpen
2026-02-01
|
| Saila: | Journal of Electrical Systems and Information Technology |
| Gaiak: | |
| Sarrera elektronikoa: | https://doi.org/10.1186/s43067-026-00324-2 |
| Etiketak: |
Etiketarik gabe, Izan zaitez lehena erregistro honi etiketa jartzen!
|