Complexity of Gaussian-radial-basis networks approximating smooth functions
From MaRDI portal
The authors approximate smooth functions on \(\mathbb R^d\) by Gaussian radial-basis function networks with units of varying widths, using \(L^2\)-distance with respect to the Lebesgue measure and derive upper bounds of rates of approximation in terms of the Bessel or Sobolev norm of the functions which are approximated. The estimates hold for all numbers of hidden unities and all degrees \(r>d/2\) of Bessel potentials. Moreover, consequences for tractability of multivariable approximation by these networks are discussed.
Recommendations
- The rate of approximation of Gaussian radial basis neural networks in continuous function space
- Gaussian radial basis functions and inner product spaces.
- scientific article; zbMATH DE number 1843036
- Gaussian radial basis functions and the approximation of input-output maps
- Almost optimal estimates for approximation and learning by radial basis function networks
Cites work
- A simple lemma on greedy approximation in Hilbert space and convergence rates for projection pursuit regression and neural network training
- Approximation by superposition of sigmoidal and radial basis functions
- Comparison of worst case errors in linear and neural network approximation
- Complexity of weighted approximation over \(\mathbb{R}^d\)
- Dimension-independent bounds on the degree of approximation by neural networks
- Dimension-independent rates of approximation by neural networks
- Error bounds for approximation with neural networks
- scientific article; zbMATH DE number 3126094 (Why is no real title available?)
- scientific article; zbMATH DE number 5008057 (Why is no real title available?)
- scientific article; zbMATH DE number 3772326 (Why is no real title available?)
- scientific article; zbMATH DE number 3611701 (Why is no real title available?)
- scientific article; zbMATH DE number 1246413 (Why is no real title available?)
- scientific article; zbMATH DE number 1988887 (Why is no real title available?)
- scientific article; zbMATH DE number 1565314 (Why is no real title available?)
- scientific article; zbMATH DE number 823880 (Why is no real title available?)
- scientific article; zbMATH DE number 3329342 (Why is no real title available?)
- Minimization of Error Functionals over Perceptron Networks
- On best approximation by ridge functions
- On the tractability of multivariate integration and approximation by neural networks
- Real Interpolation of Sobolev Spaces on Subdomains of Rn
- Sobolev error estimates and a Bernstein inequality for scattered data interpolation via radial basis functions
- Tractability and strong tractability of linear multivariate problems
- Universal approximation bounds for superpositions of a sigmoidal function
- When is approximation by Gaussian networks necessarily a linear process?
Cited in
(23)- Approximation schemes for functional optimization problems
- Learning-based complexity evaluation of radial basis function networks
- A comment on ``Relaxed conditions for radial-basis function networks to be universal approximators
- The rate of approximation of Gaussian radial basis neural networks in continuous function space
- Complexity estimates based on integral transforms induced by computational units
- Dynamic programming and value-function approximation in sequential decision problems: error analysis and numerical results
- Probabilistic lower bounds for approximation by shallow perceptron networks
- Gaussian functions combined with Kolmogorov's theorem as applied to approximation of functions of several variables
- Two fast and accurate heuristic RBF learning rules for data classification
- Complexity of shallow networks representing finite mappings
- An Integral Upper Bound for Neural Network Approximation
- Error estimates of quasi-interpolation and its derivatives
- Accuracy of approximations of solutions to Fredholm equations by kernel methods
- Can dictionary-based computational models outperform the best linear ones?
- scientific article; zbMATH DE number 2084905 (Why is no real title available?)
- scientific article; zbMATH DE number 778115 (Why is no real title available?)
- Wavelet neural networks functional approximation and application
- Some comparisons of complexity in dictionary-based and linear computational models
- Suboptimal solutions to dynamic optimization problems via approximations of the policy functions
- Lower bounds for artificial neural network approximations: a proof that shallow neural networks fail to overcome the curse of dimensionality
- New insights into Witsenhausen's counterexample
- Comparing fixed and variable-width Gaussian networks
- Estimates of variation with respect to a set and applications to optimization problems
This page was built for publication: Complexity of Gaussian-radial-basis networks approximating smooth functions
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q998978)
