Capability of neural networks in computing the outputs of dynamic systems with inputs defined on the whole space
From MaRDI portal
Publication:1267747
DOI10.1007/BF02917008zbMath0918.46027MaRDI QIDQ1267747
Publication date: 13 October 1998
Published in: Science in China. Series E (Search for Journal in Brave)
neural networks; strong theorems; equi-uniform approximation; functionals and operators in abstract spaces
92C20: Neural biology
41A65: Abstract approximation theory (approximation in normed linear spaces and other abstract spaces)
46E15: Banach spaces of continuous, differentiable or analytic functions
Cites Work
- Unnamed Item
- Approximation to continuous functions of several variables and nonlinear functions, operators by superpositions of some functions of one variable
- On the distribution of functionals of stationary Gaussian processes
- Universal approximation capability of EBF neural networks with arbitrary activation functions
- Approximations for nonlinear functions
- Approximation by superpositions of a sigmoidal function