Negative results for approximation using single layer and multilayer feedforward neural networks

DOI10.1016/J.JMAA.2020.124584OpenAlexW3087166003MaRDI QIDQ2226355FDOQ2226355

Authors: P. E. Lopez-de-Teruel, D. J. Romero-López, F. Voiglaender, Jose Maria Almira 

Publication date: 12 February 2021

Published in: Journal of Mathematical Analysis and Applications (Search for Journal in Brave)

Full work available at URL: https://arxiv.org/abs/1810.10032

Recommendations

• Approximation properties of some two-layer feedforward neural networks
• On the approximation by neural networks with bounded number of neurons in hidden layers
• scientific article; zbMATH DE number 1083116
• Approximation by neural networks with a bounded number of nodes at each level
• Limitations of the approximation capabilities of neural networks with one hidden layer

zbMATH Keywords

splinesrate of convergencerational functionsridge functionsapproximation by neural networkslethargy results

Mathematics Subject Classification ID

Artificial neural networks and deep learning (68T07) Approximation by other special function classes (41A30)

Cites Work

• Universal approximation bounds for superpositions of a sigmoidal function
• Title not available (Why is that?)
• Title not available (Why is that?)
• Multilayer feedforward networks are universal approximators
• Dependence of Computational Models on Input Dimension: Tractability of Approximation and Optimization Tasks
• Title not available (Why is that?)
• On the approximation by neural networks with bounded number of neurons in hidden layers
• Lower bounds for approximation by MLP neural networks
• Rational approximation techniques for analysis of neural networks
• Approximation schemes satisfying Shapiro's theorem
• Shapiro's theorem for subspaces
• On the tractability of multivariate integration and approximation by neural networks
• Polynomial bounds for VC dimension of sigmoidal and general Pfaffian neural networks
• 0n the best approximation by ridge functions in the uniform norm
• On the approximation by single hidden layer feedforward neural networks with fixed weights
• Best approximation by ridge functions in \(L_p\)-spaces
• Probabilistic lower bounds for approximation by shallow perceptron networks

Cited In (3)

• Extreme learning machine collocation for the numerical solution of elliptic PDEs with sharp gradients
• Expressivity of Deep Neural Networks
• Some aspects of approximation and interpolation of functions artificial neural networks

This page was built for publication: Negative results for approximation using single layer and multilayer feedforward neural networks

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q2226355)