Two $\operatorname{ReLU}$ Layers is All You Need
AI 摘要
arXiv:2610.28587v1 Announce Type: cross 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.