Integral representations of shallow neural network with Rectified Power Unit activation function

DOI10.1016/J.NEUNET.2022.09.005arXiv2112.11157WikidataQ114145524 ScholiaQ114145524MaRDI QIDQ6386309

Ahmed Abdeljawad, Philipp Grohs

Publication date: 20 December 2021

Mathematics Subject Classification ID

Learning and adaptive systems in artificial intelligence (68T05)

Related Items (1)

Two-layer networks with the \(\text{ReLU}^k\) activation function: Barron spaces and derivative approximation

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• Support theorems for the Radon transform and Cramér-Wold theorems
• Sparsest solutions of underdetermined linear systems via \( \ell _q\)-minimization for \(0<q\leqslant 1\)
• Asymptotic formulas for the dual Radon transform and applications
• Harmonic analysis of neural networks
• The Radon transform.
• Multilayer feedforward networks are universal approximators
• Complexity estimates based on integral transforms induced by computational units
• Nonparametric regression using deep neural networks with ReLU activation function
• Error bounds for approximations with deep ReLU networks
• A Sobolev-type upper bound for rates of approximation by linear combinations of Heaviside plane waves
• Integral combinations of Heavisides
• Universal approximation bounds for superpositions of a sigmoidal function
• New range theorems for the dual Radon transform
• A Course in Analysis
• Deep Neural Network Approximation Theory
• Optimal Approximation with Sparsely Connected Deep Neural Networks

This page was built for publication: Integral representations of shallow neural network with Rectified Power Unit activation function