Some comparisons of complexity in dictionary-based and linear computational models

DOI10.1016/j.neunet.2010.10.002zbMath1217.68184OpenAlexW1981815973WikidataQ51635113 ScholiaQ51635113MaRDI QIDQ553254

Giorgio Gnecco, Marcello Sanguineti, Vera Kurková

Publication date: 26 July 2011

Published in: Neural Networks (Search for Journal in Brave)

Full work available at URL: https://doi.org/10.1016/j.neunet.2010.10.002

zbMATH Keywords

neural networksmodel complexitykernel modelslinear approximation schemesvariable-basis approximation schemesworst-case errors

Mathematics Subject Classification ID

Learning and adaptive systems in artificial intelligence (68T05) Neural networks for/in biological studies, artificial life and related topics (92B20) Approximation by arbitrary linear expressions (41A45)

Related Items

Probabilistic lower bounds for approximation by shallow perceptron networks ⋮ Smart sampling and incremental function learning for very large high dimensional data ⋮ Approximation capabilities of neural networks on unbounded domains ⋮ On decision regions of narrow deep neural networks ⋮ A comparison between fixed-basis and variable-basis schemes for function approximation and functional optimization ⋮ Accuracy of approximations of solutions to Fredholm equations by kernel methods ⋮ Dynamic programming and value-function approximation in sequential decision problems: error analysis and numerical results ⋮ Correlations of random classifiers on large data sets

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Complexity of Gaussian-radial-basis networks approximating smooth functions
• Approximation schemes for functional optimization problems
• A simple lemma on greedy approximation in Hilbert space and convergence rates for projection pursuit regression and neural network training
• Geometry and topology of continuous best and near best approximations
• Random approximants and neural networks
• A Sobolev-type upper bound for rates of approximation by linear combinations of Heaviside plane waves
• On the exponential convergence of matching pursuits in quasi-incoherent dictionaries
• Geometric Upper Bounds on Rates of Variable-Basis Approximation
• Universal approximation bounds for superpositions of a sigmoidal function
• Neural Networks for Combinatorial Optimization: A Review of More Than a Decade of Research
• Negative Theorems in Approximation Theory
• Bounds on rates of variable-basis and neural-network approximation
• Comparison of worst case errors in linear and neural network approximation
• On a Variational Norm Tailored to Variable-Basis Approximation Schemes
• Error Estimates for Approximate Optimization by the Extended Ritz Method
• Continuity of approximation by neural networks in \(L_p\) spaces
• Approximating networks and extended Ritz method for the solution of functional optimization problems