Decomposing A Neural Learner
arXiv:2610.14388v1 Announce Type: new Abstract: Neural learners for classification and regression are often criticized as black boxes. We propose a probabilistic decomposition of neural learners that accounts for heterogeneous predictability across the feature space. A training procedure combining…
Read the full story at arXiv stat.ML ↗
Timeline · 1 report
- 2026-10-14 04:00 · arXiv stat.ML
Decomposing A Neural Learner