Universal approximation capability of EBF neural networks with arbitrary activation functions
From MaRDI portal
Recommendations
- L^p approximation capability of RBF neural networks
- Relaxed conditions for radial-basis function networks to be universal approximators.
- The universal approximation capabilities of double \(2\pi\)-periodic approximate identity neural networks
- Nonlinear approximations using elliptic basis function networks
- The universal approximation capabilities of cylindrical approximate identity neural networks
Cites work
- Approximation by superposition of sigmoidal and radial basis functions
- Approximation by superpositions of a sigmoidal function
- scientific article; zbMATH DE number 3329342 (Why is no real title available?)
- scientific article; zbMATH DE number 3367521 (Why is no real title available?)
- Implications and applications of Kolmogorov's superposition theorem
- Multilayer feedforward networks are universal approximators
- Nonlinear approximations using elliptic basis function networks
- Structure theorems for nonlinear systems
Cited in
(5)- Capability of neural networks in computing the outputs of dynamic systems with inputs defined on the whole space
- Nonlinear approximations using elliptic basis function networks
- Indirect adaptive control of nonlinear dynamic systems using self recurrent wavelet neural networks via adaptive learning rates
- The universal approximation capabilities of double \(2\pi\)-periodic approximate identity neural networks
- L^p approximation capability of RBF neural networks
This page was built for publication: Universal approximation capability of EBF neural networks with arbitrary activation functions
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q2563557)
