ReLU deep neural networks from the hierarchical basis perspective

DOI10.1016/j.camwa.2022.06.006OpenAlexW3162222048MaRDI QIDQ2159911

Lin Li, Juncai He, Jin-Chao Xu

Publication date: 2 August 2022

Published in: Computers \& Mathematics with Applications (Search for Journal in Brave)

Full work available at URL: https://arxiv.org/abs/2105.04156

zbMATH Keywords

finite elementapproximationexpressive powerhierarchical basisReLU DNNs

Mathematics Subject Classification ID

Artificial neural networks and deep learning (68T07) Learning and adaptive systems in artificial intelligence (68T05) Finite element, Rayleigh-Ritz and Galerkin methods for boundary value problems involving PDEs (65N30) Rate of convergence, degree of approximation (41A25) Algorithms for approximation of functions (65D15)

Related Items (2)

A deep first-order system least squares method for solving elliptic PDEs ⋮ A Hybrid Method for Three-Dimensional Semi-Linear Elliptic Equations

Uses Software

• ImageNet
• DeepXDE
• AlexNet
• DeepONet

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• A simple lemma on greedy approximation in Hilbert space and convergence rates for projection pursuit regression and neural network training
• DeepONet
• Multilayer feedforward networks are universal approximators
• Approximation rates for neural networks with general activation functions
• Exponential convergence of the deep neural network approximation for analytic functions
• Exponential ReLU DNN expression of holomorphic maps in high dimension
• Error bounds for approximations with deep ReLU networks
• Relu Deep Neural Networks and Linear Finite Elements
• Universal approximation bounds for superpositions of a sigmoidal function
• Approximation by Combinations of ReLU and Squared ReLU Ridge Functions With <inline-formula> <tex-math notation="LaTeX">$\ell^1$ </tex-math> </inline-formula> and <inline-formula> <tex-math notation="LaTeX">$\ell^0$ </tex-math> </inline-formula> Controls
• New Error Bounds for Deep ReLU Networks Using Sparse Grids
• Deep ReLU Networks Overcome the Curse of Dimensionality for Generalized Bandlimited Functions
• Deep ReLU networks and high-order finite element methods
• Error bounds for approximations with deep ReLU neural networks in Ws,p norms
• DeepXDE: A Deep Learning Library for Solving Differential Equations
• Deep Network Approximation for Smooth Functions
• Finite Neuron Method and Convergence Analysis
• Sparse grids
• Approximation by superpositions of a sigmoidal function
• Exponential ReLU neural network approximation rates for point and edge singularities

This page was built for publication: ReLU deep neural networks from the hierarchical basis perspective