Rademacher complexity and the generalization error of residual networks
From MaRDI portal
Publication:2023508
Recommendations
- Error bounds for approximations with deep ReLU networks
- Deep limits of residual neural networks
- Error bounds for ReLU networks with depth and width parameters
- Stochastic training of residual networks in deep learning
- High-dimensional dynamics of generalization error in neural networks
- scientific article; zbMATH DE number 1145911
- On the Learnability of Random Deep Networks
- Error bounds for deep ReLU networks using the Kolmogorov-Arnold superposition theorem
- Quantifying the generalization error in deep learning in terms of data distribution and neural network smoothness
Cited in
(11)- The Barron space and the flow-induced function spaces for neural network models
- Size-independent sample complexity of neural networks
- scientific article; zbMATH DE number 7625201 (Why is no real title available?)
- Nonlinear weighted directed acyclic graph and a priori estimates for neural networks
- Sparse deep neural networks using \(L_{1,\infty}\)-weight normalization
- Continuous limits of residual neural networks in case of large input data
- A Hybrid Method for Three-Dimensional Semi-Linear Elliptic Equations
- A mathematical perspective of machine learning
- Smaller generalization error derived for a deep residual neural network compared with shallow networks
- Generalization error in the deep Ritz method with smooth activation functions
- A fast neural hybrid Newton solver adapted to implicit methods for nonlinear dynamics
This page was built for publication: Rademacher complexity and the generalization error of residual networks
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q2023508)
