Approximation by neural networks with weights varying on a finite set of directions
From MaRDI portal
Publication:663685
DOI10.1016/J.JMAA.2011.11.037zbMATH Open1348.41013OpenAlexW1988019790MaRDI QIDQ663685FDOQ663685
Authors: Vugar E. Ismailov 
Publication date: 27 February 2012
Published in: Journal of Mathematical Analysis and Applications (Search for Journal in Brave)
Full work available at URL: https://doi.org/10.1016/j.jmaa.2011.11.037
Recommendations
- Approximation by neural networks with a restricted set of weights
- scientific article; zbMATH DE number 5910747
- An approximation by neural networks with a fixed weight
- Computing the approximation error for neural networks with weights varying on fixed directions
- On Approximation by Neural Networks with Optimized Activation Functions and Fixed Weights
- scientific article; zbMATH DE number 1083116
- Approximation by neural networks and learning theory
- On the approximation by single hidden layer feedforward neural networks with fixed weights
- Approximation by neural networks with a bounded number of nodes at each level
- Measure Theoretic Results for Approximation by Neural Networks with Limited Weights
Learning and adaptive systems in artificial intelligence (68T05) Approximation by other special function classes (41A30)
Cites Work
- Théorie générale des fonctions moyenne-périodiques
- Approximation by superpositions of a sigmoidal function
- Uniform approximation by neural networks
- Approximation by neural networks with a bounded number of nodes at each level
- Approximation by neural networks and learning theory
- Title not available (Why is that?)
- Lower bounds for approximation by MLP neural networks
- Approximation by Ridge functions and neural networks with one hidden layer
- Interpolation by Ridge functions
- Title not available (Why is that?)
- On the tractability of multivariate integration and approximation by neural networks
- Uniformly separating families of functions
- On the representation by linear superpositions
- Title not available (Why is that?)
- Title not available (Why is that?)
- When is \(f(x_1,x_1,\dots,x_n)= u_1(x_1)+ u_2(x_2)+\cdots+ u_n(x_n)\)?
- Some remarks on good sets
- Sums of Subalgebras of C (X )
- Uniform approximation by real functions
- On the theorem of M. Golomb
Cited In (18)
- Approximation by neural networks with a restricted set of weights
- Computing the approximation error for neural networks with weights varying on fixed directions
- Approximation by ridge functions and neural networks with a bounded number of neurons
- The construction and approximation of the neural network with two weights
- On the approximation by single hidden layer feedforward neural networks with fixed weights
- Rates of approximation by neural network interpolation operators
- Constructive approximation by neural networks with positive integer weights
- On the approximation by neural networks with bounded number of neurons in hidden layers
- Almost everywhere approximation capabilities of double Mellin approximate identity neural networks
- Neural network interpolation operators activated by smooth ramp functions
- Approximation error of single hidden layer neural networks with fixed weights
- A formula for the approximation of functions by single hidden layer neural networks with weights from two straight lines
- Approximation by sums of ridge functions with fixed directions
- On the representation by bivariate ridge functions
- Measure Theoretic Results for Approximation by Neural Networks with Limited Weights
- Approximation properties of ridge functions and extreme learning machines
- A single hidden layer feedforward network with only one neuron in the hidden layer can approximate any univariate function
- The universal approximation capabilities of double \(2\pi\)-periodic approximate identity neural networks
This page was built for publication: Approximation by neural networks with weights varying on a finite set of directions
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q663685)
