A multivariate Riesz basis of ReLU neural networks

DOI10.1016/j.acha.2023.101605arXiv2303.00076OpenAlexW4387817772MaRDI QIDQ6144893

Jan Vybíral, Cornelia Schneider

Publication date: 30 January 2024

Published in: Applied and Computational Harmonic Analysis (Search for Journal in Brave)

Full work available at URL: https://arxiv.org/abs/2303.00076

zbMATH Keywords

Möbius functionRiesz basisartificial neural networksEuler productrectified linear unit

Mathematics Subject Classification ID

Artificial neural networks and deep learning (68T07) General harmonic expansions, frames (42C15) Arithmetic functions; related numbers; inversion formulas (11A25)

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• Frames and the projection method
• New characterizations of Riesz bases
• Foundations of time-frequency analysis
• Frames containing a Riesz basis and approximation of the frame coefficients using finite-dimensional methods
• Nonlinear approximation and (deep) ReLU networks
• Approximation spaces of deep neural networks
• Optimal approximation of piecewise smooth functions using deep ReLU neural networks
• Nonparametric regression using deep neural networks with ReLU activation function
• Error bounds for approximations with deep ReLU networks
• Matrix Analysis
• DeepStack: Expert-level artificial intelligence in heads-up no-limit poker
• Deep Neural Network Approximation Theory
• Optimal Approximation with Sparsely Connected Deep Neural Networks
• Neural network approximation
• An introduction to frames and Riesz bases
• Deep ReLU neural networks in high-dimensional approximation

This page was built for publication: A multivariate Riesz basis of ReLU neural networks