Score: 0

Maxout Polytopes

Published: September 25, 2025 | arXiv ID: 2509.21286v1

By: Andrei Balakin , Shelby Cox , Georg Loho and more

Potential Business Impact:

Makes computer brains learn faster and better.

Business Areas:
Multi-level Marketing Sales and Marketing

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.

Page Count
24 pages

Category
Mathematics:
Combinatorics