NewA calmer, faster ZeroHour — security assessments on articles, story timelines and search from any page.

#relu-networks

0 stories this week · 1 this month · 2 in 6 months · mostly AI

Stories per day · 30 days

Relatedexpressivity1 neural-networks1 piecewise-linear1

2 stories, newest first · one card per story

arXiv cs.AI / cs.LG / cs.CL23d ago

Caterpillar Net represents maxima with two hidden layers

The nonrecursive construction uses hidden-layer widths O(N squared) and 2 to the O(N log N).

relu-networks expressivity

arXiv cs.AI / cs.LG / cs.CLSep 8, 2026

Nearly Tight Rademacher Bounds for Sparsely Activated Neural Networks

Theory paper derives nearly tight Rademacher complexity bounds for sparsely activated one-hidden-layer ReLU networks.

generalization-bounds learning-theory

2