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...

Ausführliche Beschreibung

Bibliografische Detailangaben

1. Verfasser:	A. Sushiiel
Format:	Artigo
Sprache:	Inglês
Veröffentlicht:	SpringerOpen 2026-02-01
Schriftenreihe:	Journal of Electrical Systems and Information Technology
Schlagworte:	Explainable AI Fair machine learning Neural network interpretability Additive models Statistical equivalence testing Algorithmic accountability
Online-Zugang:	https://doi.org/10.1186/s43067-026-00324-2
Tags:	Tag hinzufügen Keine Tags, Fügen Sie das erste Tag hinzu!