Signals 4 · free daily AI digest

Two $\operatorname{ReLU}$ Layers is All You Need

Paper recorded by Signals 4 on 2026-10-20 in cs.LG. Abstract reproduced from arXiv; link to the original below.

Published 2026-10-20 on arXiv · recorded by Signals 4 on 2026-10-21

Category: cs.LG · 机器学习 · first seen 2026-10-21

Abstract

We prove that every $\operatorname{ReLU}$ network can be exactly simulated by a $\operatorname{ReLU}$ network with two hidden layers. We present two proofs: one that is based on fillings in homological algebra and a direct combinatorial proof.

Read on arXiv →

#225 most recent of 749 cs.LG papers we have recorded · ↑ newer: WildMAE: Structure-Aware Masked Autoencoding for Wildlife Image Recons · ↓ older: Continuous-Time Policy Gradient from Discrete Data: Convergence Analys
Cite this page: Two $\operatorname{ReLU}$ Layers is All You Need: the #225 most recent of 749 cs.LG papers we have recorded (as of 2026-10-20). Source: Signals 4 (Signals API) — https://data.jiangzhang.ca/signals4/t/papers/two-operatorname-relu-layers-is-all-you-need.html
Free to quote with attribution to “Signals 4 (Signals API)”. Machine-readable: papers.json
Related: More cs.LG papers · arXiv signals · All papers · Today in AI
Get 4 AI signals a day by email — free.
Subscribe free → See all plans →
Get 4 AI signals a day by email — free
All models · All repos · By company · Daily editions