Spline representation and redundancies of one-dimensional ReLU neural network models

DOI10.1142/S0219530522400103MaRDI QIDQ5873929zbMATH OpenFDO

Authors Yannick Riebe, Gerlind Plonka, Yu. S. Kolomoitsev

Publication date 10 February 2023

Published in Analysis and Applications (Search for Journal in Brave)

Full work available at URL https://arxiv.org/abs/2207.14609

zbMATH Keywords

recursive algorithmparameter redundanciesfree knot spline functionsReLU deep neural network

Mathematics Subject Classification ID

Artificial neural networks and deep learning (68T07) Numerical interpolation (65D05) Spline approximation (41A15)

Recommendations

• Neural splines: exploiting parallelism for function approximation using modular neural networks
• Approximation by Ridge functions and neural networks with one hidden layer
• ExSpliNet: An interpretable and expressive spline-based neural network
• Banach space representer theorems for neural networks and ridge splines
• Approximation Algorithms for Training One-Node ReLU Neural Networks
• Nonlinear approximation and (deep) ReLU networks

Cites work

• scientific article; zbMATH DE number 1215245 (Why is no real title available?)
• scientific article; zbMATH DE number 1405266 (Why is no real title available?)
• A practical guide to splines.
• Approximation by superpositions of a sigmoidal function
• Deep Network Approximation for Smooth Functions
• Deep network approximation characterized by number of neurons
• Deep neural networks for rotation-invariance approximation and learning
• Error bounds for approximations with deep ReLU networks
• Multilayer feedforward networks are universal approximators
• Neural Networks for Localized Approximation
• Neural network approximation
• Nonlinear approximation and (deep) ReLU networks
• Optimal approximation of piecewise smooth functions using deep ReLU neural networks
• Optimal approximation with sparsely connected deep neural networks
• Universality of deep convolutional neural networks

Cited in

(8)

• Why rectified linear activation functions? Why max-pooling? A possible explanation
• Neural splines: exploiting parallelism for function approximation using modular neural networks
• A representer theorem for deep neural networks
• Relevant sampling in a reproducing kernel subspace of Orlicz space
• Approximation of Lipschitz Functions Using Deep Spline Neural Networks
• ReLU deep neural networks and linear finite elements
• Spline Representation and Redundancies of One-Dimensional ReLU Neural Network Models
• An embedding of ReLU networks and an analysis of their identifiability

This page was built for publication: Spline representation and redundancies of one-dimensional ReLU neural network models

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q5873929)