Universal approximation capability of EBF neural networks with arbitrary activation functions
From MaRDI portal
Publication:2563557
DOI10.1007/BF01188988zbMath0860.68086MaRDI QIDQ2563557
Publication date: 16 December 1996
Published in: Circuits, Systems, and Signal Processing (Search for Journal in Brave)
68T05: Learning and adaptive systems in artificial intelligence
Related Items
The universal approximation capabilities of double \(2\pi\)-periodic approximate identity neural networks, \(L^p\) approximation capability of RBF neural networks, Capability of neural networks in computing the outputs of dynamic systems with inputs defined on the whole space, Indirect adaptive control of nonlinear dynamic systems using self recurrent wavelet neural networks via adaptive learning rates
Cites Work
- Structure theorems for nonlinear systems
- Approximation by superposition of sigmoidal and radial basis functions
- Nonlinear approximations using elliptic basis function networks
- Multilayer feedforward networks are universal approximators
- Implications and applications of Kolmogorov's superposition theorem
- Approximation by superpositions of a sigmoidal function
- Unnamed Item
- Unnamed Item