Deep Network Approximation Characterized by Number of Neurons (Q5162359)

scientific article; zbMATH DE number 7419151

Language	Label	Description	Also known as
English	Deep Network Approximation Characterized by Number of Neurons	scientific article; zbMATH DE number 7419151

Statements

instance of

scholarly article

0 references

title

Deep Network Approximation Characterized by Number of Neurons (English)

0 references

0 references

0 references

0 references

Communications in Computational Physics

0 references

publication date

2 November 2021

0 references

full work available at URL

https://arxiv.org/abs/1906.05497

0 references

zbMATH Keywords

deep ReLU neural networks

0 references

Hölder continuity

0 references

modulus of continuity

0 references

approximation theory

0 references

low-dimensional manifold

0 references

parallel computing

0 references

describes a project that uses

ImageNet

0 references

MaRDI profile type

MaRDI publication profile

0 references

cites work

Random projections of smooth manifolds

0 references

Universal approximation bounds for superpositions of a sigmoidal function

0 references

Q3805940

0 references

Saturation classes for MAX-product neural network operators activated by sigmoidal functions

0 references

Convergence for a family of neural network operators in Orlicz spaces

0 references

Approximation results in Orlicz spaces for sequences of Kantorovich MAX-product neural network operators

0 references

Approximation by superpositions of a sigmoidal function

0 references

Approximation using scattered shifts of a multivariate function

0 references

Deep learning-based numerical methods for high-dimensional parabolic partial differential equations and backward stochastic differential equations

0 references

A priori estimates of the population risk for two-layer neural networks

0 references

Solving high-dimensional partial differential equations using deep learning

0 references

Nonlinear approximation using Gaussian kernels

0 references

Multilayer feedforward networks are universal approximators

0 references

A proof that rectified deep neural networks overcome the curse of dimensionality in the numerical approximation of semilinear heat equations

0 references

Efficient distribution-free learning of probabilistic concepts

0 references

Approximation of functions of finite variation by superpositions of a sigmoidal function.

0 references

Almost optimal estimates for approximation and learning by radial basis function networks

0 references

Constructive approximate interpolation by neural networks

0 references

Lower bounds for approximation by MLP neural networks

0 references

Matching pursuits with time-frequency dictionaries

0 references

Extension of range of functions

0 references

New Error Bounds for Deep ReLU Networks Using Sparse Grids

0 references

Error bounds for deep ReLU networks using the Kolmogorov-Arnold superposition theorem

0 references

Optimal approximation of piecewise smooth functions using deep ReLU neural networks

0 references

Multivariate \(n\)-term rational and piecewise polynomial approximation

0 references

Nonparametric regression using deep neural networks with ReLU activation function

0 references

Provable approximation properties for deep neural networks

0 references

Nonlinear approximation via compositions

0 references

The rate of approximation of Gaussian radial basis neural networks in continuous function space

0 references

Error bounds for approximations with deep ReLU networks

0 references

Identifiers

Mathematics Subject Classification ID

0 references

0 references

0 references

0 references

10.4208/CICP.OA-2020-0149

0 references

Sitelinks

Mathematics(1 entry)

mardi Publication:5162359