Approximation properties of deep ReLU CNNs
From MaRDI portal
Publication:2157922
Recommendations
Cites work
- 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
- Approximation by superpositions of a sigmoidal function
- Approximation rates for neural networks with general activation functions
- Breaking the curse of dimensionality with convex neural networks
- Deep distributed convolutional neural networks: universality
- Deep learning
- Deep ReLU networks and high-order finite element methods
- Equivalence of approximation by convolutional neural networks and fully-connected networks
- Error bounds for approximations with deep ReLU networks
- Error bounds for approximations with deep ReLU neural networks in \(W^{s , p}\) norms
- Finite neuron method and convergence analysis
- High-order approximation rates for shallow neural networks with cosine and \(\mathrm{ReLU}^k\) activation functions
- MgNet: a unified framework of multigrid and convolutional neural network
- Multilayer feedforward networks are universal approximators
- Nonlinear approximation via compositions
- ReLU deep neural networks and linear finite elements
- Ten Lectures on Wavelets
- Universal approximation bounds for superpositions of a sigmoidal function
- Universal Consistency of Deep Convolutional Neural Networks
- Universality of deep convolutional neural networks
Cited in
(28)- The universal approximation property. Characterization, construction, representation, and existence
- Constructive deep ReLU neural network approximation
- Approximation spaces of deep neural networks
- ReLU deep neural networks from the hierarchical basis perspective
- A global universality of two-layer neural networks with ReLU activations
- ReLU networks are universal approximators via piecewise linear or constant functions
- Lipschitz properties for deep convolutional networks
- Deep Neural Network Approximation Theory
- Deep ReLU Networks Overcome the Curse of Dimensionality for Generalized Bandlimited Functions
- A note on the applications of one primary function in deep neural networks
- Butterfly-net: optimal function representation based on convolutional neural networks
- On minimal representations of shallow ReLU networks
- Convergence of deep convolutional neural networks
- Approximation Analysis of Convolutional Neural Networks
- Towards Lower Bounds on the Depth of ReLU Neural Networks
- MorphoActivation: generalizing ReLU activation function by mathematical morphology
- A Note on the Regularity of Images Generated by Convolutional Neural Networks
- Error bounds for approximations using multichannel deep convolutional neural networks with downsampling
- Forward and inverse approximation theory for linear temporal convolutional networks
- Approximation in shift-invariant spaces with deep ReLU neural networks
- An Interpretive Constrained Linear Model for ResNet and MgNet
- Approximation of classifiers by deep perceptron networks
- Approximation analysis of CNNs from a feature extraction view
- An enhanced V-cycle MgNet model for operator learning in numerical partial differential equations
- Universal approximation property of fully convolutional neural networks with zero padding
- Two-dimensional deep ReLU CNN approximation for Korobov functions: a constructive approach
- On the expressive power of deep 2D ReLU convolutional neural networks
- Operator inference for elliptic eigenvalue problems
This page was built for publication: Approximation properties of deep ReLU CNNs
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q2157922)
