A Framework for the Construction of Upper Bounds on the Number of Affine Linear Regions of ReLU Feed-Forward Neural Networks

DOI10.1109/TIT.2019.2927252zbMath1433.94008arXiv1806.01918OpenAlexW2963657672MaRDI QIDQ5211507

Sara van de Geer, Peter Hinz

Publication date: 28 January 2020

Published in: IEEE Transactions on Information Theory (Search for Journal in Brave)

Full work available at URL: https://arxiv.org/abs/1806.01918

zbMATH Keywords

upper boundsnumber of regionsaffine linear feed-forward neural networks with ReLU activation functions

Mathematics Subject Classification ID

Communication theory (94A05)

Related Items (2)

Sharp Bounds for the Number of Regions of Maxout Networks and Vertices of Minkowski Sums ⋮ On the number of regions of piecewise linear neural networks

This page was built for publication: A Framework for the Construction of Upper Bounds on the Number of Affine Linear Regions of ReLU Feed-Forward Neural Networks