Explorer›Data Science›Machine Learning
Research PaperResearchia:202610.21063

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

Florestan Brunck

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. --- Source: arXiv:2610.28587v1 - http://arxiv.org/abs/2610.28587v1 PDF: https://arxiv.org/pdf/2610.28587v1 Original Link: http://arxiv.org/abs/2610.28587v1

Submitted: October 21, 2026Subjects: Machine Learning; Data Science

Description / Details

We prove that every ReLU⁡\operatorname{ReLU} network can be exactly simulated by a ReLU⁡\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.


Source: arXiv:2610.28587v1 - http://arxiv.org/abs/2610.28587v1 PDF: https://arxiv.org/pdf/2610.28587v1 Original Link: http://arxiv.org/abs/2610.28587v1

Please sign in to join the discussion.

No comments yet. Be the first to share your thoughts!

Access Paper
View Source PDF
Submission Info
Date:
Oct 21, 2026
Topic:
Data Science
Area:
Machine Learning
Comments:
0
Bookmark
Two $\operatorname{ReLU}$ Layers is All You Need | Researchia