An approximation by neural networks with a fixed weight
A function \(\sigma: {\mathbb R} \to {\mathbb R}\) is called sigmoidal if \(\lim_ {x\to -\infty} \sigma(x)=0\), \(\lim_ {x\to +\infty} \sigma(x)=1\). Theorem 1. Let \(\sigma\) be a bounded sigmoidal function on \({\mathbb R}\) and let \(\epsilon >0\) be given. If \(f\) is a continuous function on \({\mathbb R}\) such that \(\lim_{| x| \to \infty} f(x)=0\), then there exist constants \(b_i, c_i \in {\mathbb R}\) and positive integers \(N,K\) such that \[ \left | f(x)-\sum_{i=1}^N c_i \sigma (Kx+b_i)\right | <\epsilon, \qquad x \in {\mathbb R}. \] Another similar theorem is also proved and some numerical examples are given.
- Neural-network approximation of functions of several variables
- On the approximation by single hidden layer feedforward neural networks with fixed weights
- Approximation by neural networks with sigmoidal functions
- Approximation by neural networks with a generalized sigmoidal function
- Constructive approximation by neural networks with positive integer weights
- Approximation by Ridge functions and neural networks with one hidden layer
- Approximation by superpositions of a sigmoidal function
- Extension of localised approximation by neural networks
- scientific article; zbMATH DE number 66819 (Why is no real title available?)
- Universal approximation bounds for superpositions of a sigmoidal function
- A comparative analysis of neural network performances in astronomical imaging
- Approximation by exponential sampling type neural network operators
- Rates of approximation by neural network interpolation operators
- The construction and approximation of ReLU neural network operators
- Sigmoidal approximations of a nonautonomous neural network with infinite delay and Heaviside function
- On the approximation by single hidden layer feedforward neural networks with fixed weights
- Extreme learning machine collocation for the numerical solution of elliptic PDEs with sharp gradients
- Quantitative approximation by perturbed Kantorovich-Choquet neural network operators
- Weight adjustment rule of neural networks for computing discrete 2-D Gabor transforms (image processing)
- Approximation by neural networks with sigmoidal functions
- scientific article; zbMATH DE number 1293729 (Why is no real title available?)
- scientific article; zbMATH DE number 647659 (Why is no real title available?)
- scientific article; zbMATH DE number 740111 (Why is no real title available?)
- Approximation by neural networks with a generalized sigmoidal function
- Neural network interpolation operators activated by smooth ramp functions
- Degree of multivariate approximation by superposition of a sigmoidal function
- Function approximation of Seidel aberrations by a neural network
- Constructive approximation by neural networks with positive integer weights
- Approximation by perturbed neural network operators
- Approximations by multivariate perturbed neural network operators
- Multivariate sigmoidal neural network approximation
- On Approximation by Neural Networks with Optimized Activation Functions and Fixed Weights
- On sigmoidal functions
- Approximation by neural networks with weights varying on a finite set of directions
- Construction and approximation properties of exact neural network interpolation operators activated by entire functions
- Approximation of neural network operators based on the Joukowski transformation
- The approximation operators with sigmoidal functions
This page was built for publication: An approximation by neural networks with a fixed weight
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q1767906)
