Coverage regularization in minimal MLPs yields lower prototype reconstruction error and higher specialization than baseline or repulsive losses on 1D data from N=3 to 100.
Title resolution pending
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
fields
cs.LG 2years
2026 2representative citing papers
citing papers explorer
-
From Latent Space to Training Data: Explainable Specialization in Minimal MLPs
Coverage regularization in minimal MLPs yields lower prototype reconstruction error and higher specialization than baseline or repulsive losses on 1D data from N=3 to 100.
- Pretrained Approximators for Low-Thrust Trajectory Cost and Reachability