Dimension-independent rates of approximation by neural networks
From MaRDI portal
(Redirected from Dimension-independent rates of approximation by neural networks)
In studying the approximation of multivariable functions by neural networks with dimension-independent rates of approximation, the author introduces a norm called variation with respect to a family of functions and derives its basic properties. Upper estimates on variation with respect to half-spaces are given, and the estimates are extended to variations with respect to more general activation functions. For the entire collection see [Zbl 0892.00024].
Recommendations
Cited in
(27)- Complexity estimates based on integral transforms induced by computational units
- Approximation rates for neural networks with general activation functions
- Approximation rates for neural networks with encodable weights in smoothness spaces
- High-dimensional dynamics of generalization error in neural networks
- Some implications of interval approach to dimension for network complexity
- Uniform approximation rates and metric entropy of shallow neural networks
- Estimates of covering numbers of convex sets with slowly decaying orthogonal subsets
- A Sobolev-type upper bound for rates of approximation by linear combinations of Heaviside plane waves
- Rates of approximation by neural networks with four layers
- scientific article; zbMATH DE number 1225807 (Why is no real title available?)
- Dimension-independent bounds on the degree of approximation by neural networks
- Bounds on rates of variable-basis and neural-network approximation
- Can dictionary-based computational models outperform the best linear ones?
- Improved rates and asymptotic normality for nonparametric neural network estimators
- Some comparisons between linear approximation and approximation by neural networks
- On convergence rate of projection neural networks
- Measure Theoretic Results for Approximation by Neural Networks with Limited Weights
- Geometric Rates of Approximation by Neural Networks
- Some comparisons of complexity in dictionary-based and linear computational models
- Learning with generalization capability by kernel methods of bounded complexity
- Deep learning: a statistical viewpoint
- Lower bounds for artificial neural network approximations: a proof that shallow neural networks fail to overcome the curse of dimensionality
- Unlocking Your Bike the Easy Way
- Approximation error estimates by noise-injected neural networks
- On the rate of convergence in topology preserving neural networks
- Lower estimation of approximation rate for neural networks
- Complexity of Gaussian-radial-basis networks approximating smooth functions
This page was built for publication: Dimension-independent rates of approximation by neural networks
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q4400833)
