Approximation of smooth functionals using deep ReLU networks

DOI10.1016/J.NEUNET.2023.07.012MaRDI QIDQ6488836

Jun Fan, Linhao Song, Ying Liu, Ding-Xuan Zhou

Publication date: 26 October 2023

Published in: Neural Networks (Search for Journal in Brave)

zbMATH Keywords

Fréchet derivativeapproximation theorysmooth functionalsReLUdeep learning theorypolynomial rates

Mathematics Subject Classification ID

Artificial intelligence (68Txx) Nonparametric inference (62Gxx) Approximations and expansions (41Axx)

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Functional linear regression analysis for longitudinal data
• Single and multiple index functional regression models with nonparametric link
• Multilayer feedforward networks are universal approximators
• Provable approximation properties for deep neural networks
• Functional multi-layer perceptron: A nonlinear tool for functional data analysis
• Postmodern analysis.
• Approximation properties of a multilayered feedforward artificial neural network
• Limitations of the approximation capabilities of neural networks with one hidden layer
• Online gradient descent algorithms for functional data learning
• DeepM\&Mnet: inferring the electroconvection multiphysics fields based on operator approximation by neural networks
• Optimal approximation of piecewise smooth functions using deep ReLU neural networks
• Error bounds for approximations with deep ReLU networks
• Universality of deep convolutional neural networks
• Data-driven operator inference for nonintrusive projection-based model reduction
• Neural Networks for Functional Approximation and System Identification
• On Some Extremal Functions and their Applications in the Theory of Analytic Functions of Several Complex Variables
• Universal approximation bounds for superpositions of a sigmoidal function
• Deep distributed convolutional neural networks: Universality
• 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
• Solving parametric PDE problems with artificial neural networks
• Optimal Approximation with Sparsely Connected Deep Neural Networks
• Error estimates for DeepONets: a deep learning framework in infinite dimensions
• Deep Network Approximation Characterized by Number of Neurons
• Approximation by superpositions of a sigmoidal function
• Approximation of nonlinear functionals using deep ReLU networks

This page was built for publication: Approximation of smooth functionals using deep ReLU networks