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...

Description complète

Détails bibliographiques

Auteur principal:	A. Sushiiel
Format:	Artigo
Langue:	Inglês
Publié:	SpringerOpen 2026-02-01
Collection:	Journal of Electrical Systems and Information Technology
Sujets:	Explainable AI Fair machine learning Neural network interpretability Additive models Statistical equivalence testing Algorithmic accountability
Accès en ligne:	https://doi.org/10.1186/s43067-026-00324-2
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!