Piecewise linear functions representable with infinite width shallow ReLU neural networks

DOI10.1090/bproc/186arXiv2307.14373OpenAlexW4386957178MaRDI QIDQ6052562

Sarah McCarty

Publication date: 17 October 2023

Published in: Proceedings of the American Mathematical Society, Series B (Search for Journal in Brave)

Full work available at URL: https://arxiv.org/abs/2307.14373

zbMATH Keywords

shallow networksReLU networks

Mathematics Subject Classification ID

Artificial neural networks and deep learning (68T07)

Cites Work

• Harmonic analysis of neural networks
• Hidden unit specialization in layered neural networks: ReLU vs. sigmoidal activation
• Representation formulas and pointwise properties for Barron functions
• A priori estimates of the population risk for two-layer neural networks
• Neural network with unbounded activation functions is universal approximator
• Relu Deep Neural Networks and Linear Finite Elements
• Large Intersections of Large Sets
• On the σ-class generated by open balls
• Breaking the Curse of Dimensionality with Convex Neural Networks
• The Ridgelet transform of distributions
• Approximation by superpositions of a sigmoidal function
• Probability theory. A comprehensive course

This page was built for publication: Piecewise linear functions representable with infinite width shallow ReLU neural networks