Researchers introduce ONAM for fitting orthogonal neural additive models to interpret black-box predictions
A new paper on arXiv presents ONAM, a method for fitting orthogonal neural additive models to provide post-hoc interpretability of complex black-box machine learning predictions.
Read the full story at arXiv stat.ML ↗
Timeline · 1 report
- 2026-11-17 05:00 · arXiv stat.ML
ONAM: Fitting Orthogonal Neural Additive Models for Post-Hoc Interpretability of Black-Box Predictions