Salvato in:
Dettagli Bibliografici
Autori principali: Balakin, Andrei, Cox, Shelby, Loho, Georg, Sturmfels, Bernd
Natura: Preprint
Pubblicazione: 2025
Soggetti:
Accesso online:https://arxiv.org/abs/2509.21286
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866915513928515584
author Balakin, Andrei
Cox, Shelby
Loho, Georg
Sturmfels, Bernd
author_facet Balakin, Andrei
Cox, Shelby
Loho, Georg
Sturmfels, Bernd
contents Maxout polytopes are defined by feedforward neural networks with maxout activation function and non-negative weights after the first layer. We characterize the parameter spaces and extremal f-vectors of maxout polytopes for shallow networks, and we study the separating hypersurfaces which arise when a layer is added to the network. We also show that maxout polytopes are cubical for generic networks without bottlenecks.
format Preprint
id arxiv_https___arxiv_org_abs_2509_21286
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Maxout Polytopes
Balakin, Andrei
Cox, Shelby
Loho, Georg
Sturmfels, Bernd
Combinatorics
Discrete Mathematics
Machine Learning
Maxout polytopes are defined by feedforward neural networks with maxout activation function and non-negative weights after the first layer. We characterize the parameter spaces and extremal f-vectors of maxout polytopes for shallow networks, and we study the separating hypersurfaces which arise when a layer is added to the network. We also show that maxout polytopes are cubical for generic networks without bottlenecks.
title Maxout Polytopes
topic Combinatorics
Discrete Mathematics
Machine Learning
url https://arxiv.org/abs/2509.21286