Updated study examines how ReLU network parameters grow when approximating smooth functions
A revised arXiv paper analyzes fully connected feed-forward ReLU neural networks approximating a given smooth function, focusing on how their parameters grow.
Read the full story at arXiv cs.LG ↗
Timeline · 1 report
- 2026-11-04 05:00 · arXiv cs.LG
On the growth of the parameters of approximating ReLU neural networks