On decision regions of narrow deep neural networks

DOI10.1016/j.neunet.2021.02.024zbMath1522.68492arXiv1807.01194OpenAlexW3135649730MaRDI QIDQ6078750

Hans-Peter Beise, Steve Dias Da Cruz, U. Schroeder

Publication date: 28 September 2023

Published in: Neural Networks (Search for Journal in Brave)

Full work available at URL: https://arxiv.org/abs/1807.01194

zbMATH Keywords

neural networksexpressive powerdecision regionsapproximation by network functionswidth of neural networks

Mathematics Subject Classification ID

Artificial neural networks and deep learning (68T07) Rate of convergence, degree of approximation (41A25) Approximation by other special function classes (41A30)

Related Items (1)

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

Cites Work

• Unnamed Item
• Approximation results for neural network operators activated by sigmoidal functions
• Some comparisons of complexity in dictionary-based and linear computational models
• Why does deep and cheap learning work so well?
• On the approximation by single hidden layer feedforward neural networks with fixed weights
• Optimal approximation of piecewise smooth functions using deep ReLU neural networks
• Error bounds for approximations with deep ReLU networks
• Deep vs. shallow networks: An approximation theory perspective
• Optimal Approximation with Sparsely Connected Deep Neural Networks
• Error bounds for approximations with deep ReLU neural networks in Ws,p norms
• Equivalence of approximation by convolutional neural networks and fully-connected networks
• Approximation by superpositions of a sigmoidal function

This page was built for publication: On decision regions of narrow deep neural networks