Approximation Analysis of Convolutional Neural Networks
From MaRDI portal
Recommendations
- Approximation properties of deep ReLU CNNs
- Approximation analysis of CNNs from a feature extraction view
- Theory of deep convolutional neural networks. III: Approximating radial functions
- Universality of deep convolutional neural networks
- Deep vs. shallow networks: an approximation theory perspective
Cites work
- A mathematical introduction to compressive sensing
- A Mathematical Theory of Deep Convolutional Neural Networks for Feature Extraction
- Approximation and estimation bounds for artificial neural networks
- Approximation by superpositions of a sigmoidal function
- Approximation of frame based missing data recovery
- Convolutional neural networks analyzed via convolutional sparse coding
- Data-driven tight frame construction and image denoising
- Decoding by Linear Programming
- Deep belief networks are compact universal approximators
- Deep network approximation characterized by number of neurons
- Deep Neural Networks with Random Gaussian Weights: A Universal Classification Strategy?
- Deep vs. shallow networks: an approximation theory perspective
- Group invariant scattering
- scientific article; zbMATH DE number 1332320 (Why is no real title available?)
- Multiscale adaptive representation of signals. I: The basic framework
- On the mathematical foundations of learning
- Provable approximation properties for deep neural networks
- Refinements of universal approximation results for deep belief networks and restricted Boltzmann machines
- Representational Power of Restricted Boltzmann Machines and Deep Belief Networks
- The restricted isometry property and its implications for compressed sensing
- Universal approximation bounds for superpositions of a sigmoidal function
- Universality of deep convolutional neural networks
Cited in
(9)- Theory of deep convolutional neural networks. II: Spherical analysis
- Error Analysis and Improving the Accuracy of Winograd Convolution for Deep Neural Networks
- On Lipschitz Bounds of General Convolutional Neural Networks
- Forward and inverse approximation theory for linear temporal convolutional networks
- Hyper-flexible convolutional neural networks based on generalized Lehmer and power means
- Approximation analysis of CNNs from a feature extraction view
- Function space and critical points of linear convolutional networks
- Why shallow networks struggle to approximate and learn high frequencies
- On the universal approximation property of deep fully convolutional neural networks
This page was built for publication: Approximation Analysis of Convolutional Neural Networks
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6090346)
