Approximation problems in system identification with neural networks
The capability of approximating continuous functions of several variables by neural nets is investigated. Starting from a result by Cybenko concerning the denseness of linear combinations of continuous sigmoidal functions in \(L^ p (K)\), the author finally proves -- in the framework of \(L^ p\)-Tauber-Wiener functions -- that by composition of some functions of one variable, one can approximate continuous functionals defined on compact \(L^ p (K)\), and continuous operators from compact \(L^ p (K_ 1)\) to \(L^ p (K_ 2)\).
- Neural Networks for Functional Approximation and System Identification
- L^p (K) approximation problems in system identification with RBF neural networks
- Capability of neural networks in computing the outputs of dynamic systems with inputs defined on the whole space
- Neural networks for optimal approximation of continuous functions in \(\mathbb R^d\)
- scientific article; zbMATH DE number 1989737
- Approximating nonlinear fading-memory operators using neural network models
- Capability of neural networks in computing the outputs of dynamic systems with inputs defined on the whole space
- Approximation to functions of several variables by superpositions of functions of fewer variables
- AR parameter estimation by a feedback neural network
- Neural network approach to the TLS linear prediction frequency estimation problem
- The essential order of approximation for nearly exponential type neural networks
- Neural Networks for Functional Approximation and System Identification
- L^p (K) approximation problems in system identification with RBF neural networks
- Neural network for system identification
- scientific article; zbMATH DE number 1293729 (Why is no real title available?)
- Neural network approach for identification of Hammerstein systems
- Neural Networks and Identification of Systems With Unobserved States
- of overparametrization in non-linear system identification and neural networks
- On approximation of linear functionals on L/sub p/ spaces
- Neural networks and the best trigomometric approximation
- Optimal estimation of parameters of dynamical systems by neural network collocation method
- Lower estimation of approximation rate for neural networks
This page was built for publication: Approximation problems in system identification with neural networks
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q1334039)
