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

DOI10.1016/j.jmaa.2020.124584OpenAlexW3087166003MaRDI QIDQ2226355

D. J. Romero-López, F. Voiglaender, P. E. Lopez-de-Teruel, J. M. Almira Picazo

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

zbMATH Keywords

rate of convergencesplinesrational functionsridge functionsapproximation by neural networkslethargy results

Mathematics Subject Classification ID

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

Related Items (2)

Some aspects of approximation and interpolation of functions artificial neural networks ⋮ Extreme learning machine collocation for the numerical solution of elliptic PDEs with sharp gradients

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• Approximation schemes satisfying Shapiro's theorem
• On the approximation by neural networks with bounded number of neurons in hidden layers
• Shapiro's theorem for subspaces
• Polynomial bounds for VC dimension of sigmoidal and general Pfaffian neural networks
• On the tractability of multivariate integration and approximation by neural networks
• Lower bounds for approximation by MLP neural networks
• Multilayer feedforward networks are universal approximators
• On the approximation by single hidden layer feedforward neural networks with fixed weights
• Probabilistic lower bounds for approximation by shallow perceptron networks
• Best approximation by ridge functions in L p -spaces
• Universal approximation bounds for superpositions of a sigmoidal function
• Rational approximation techniques for analysis of neural networks
• Dependence of Computational Models on Input Dimension: Tractability of Approximation and Optimization Tasks
• 0n the best approximation by ridge functions in the uniform norm

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