On Transversality of Bent Hyperplane Arrangements and the Topological Expressiveness of ReLU Neural Networks

DOI10.1137/20M1368902MaRDI QIDQ5073711FDOQ5073711

Authors: Elisenda Grigsby, Kathryn Lindsey 

Publication date: 3 May 2022

Published in: SIAM Journal on Applied Algebra and Geometry (Search for Journal in Brave)

Full work available at URL: https://arxiv.org/abs/2008.09052

Recommendations

• On decision regions of narrow deep neural networks
• On minimal representations of shallow ReLU networks
• Topology of deep neural networks
• Towards Lower Bounds on the Depth of ReLU Neural Networks
• Facets of neural network complexity

zbMATH Keywords

polyhedral complexesReLU neural networkstopological expressiveness

Mathematics Subject Classification ID

Artificial neural networks and deep learning (68T07) Polyhedral manifolds (52B70) Arrangements of points, flats, hyperplanes (aspects of discrete geometry) (52C35) Critical points and critical submanifolds in differential topology (57R70) PL-topology (57Q99)

Cites Work

• Lectures on Polytopes
• Title not available (Why is that?)
• An introduction to hyperplane arrangements
• Convex Polytopes
• Approximation by superpositions of a sigmoidal function
• Lower Bounds for Approximation by Nonlinear Manifolds
• Facing up to arrangements: face-count formulas for partitions of space by hyperplanes
• Reconciling modern machine-learning practice and the classical bias-variance trade-off
• On decision regions of narrow deep neural networks

Cited In (3)

• Labeled sample compression schemes for complexes of oriented matroids
• Topological properties of basins of attraction of width bounded autoencoders
• Sharp Bounds for the Number of Regions of Maxout Networks and Vertices of Minkowski Sums

This page was built for publication: On Transversality of Bent Hyperplane Arrangements and the Topological Expressiveness of ReLU Neural Networks

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q5073711)