Can dictionary-based computational models outperform the best linear ones?

DOI10.1016/J.NEUNET.2011.05.014MaRDI QIDQ456017zbMATH OpenOpenAlexDBLPWikidataFDO

Authors Giorgio Gnecco, Marcello Sanguineti, Věra Kůrková

Publication date 23 October 2012

Published in Neural Networks (Search for Journal in Brave)

Full work available at URL https://doi.org/10.1016/j.neunet.2011.05.014

zbMATH Keywords

linear approximationKolmogorov widthworst-case errordictionary-based approximationperceptron networksrates of approximation

Mathematics Subject Classification ID

Learning and adaptive systems in artificial intelligence (68T05) Stochastic approximation (62L20) Neural networks for/in biological studies, artificial life and related topics (92B20) Programming in abstract spaces (90C48)

Recommendations

• Some comparisons of complexity in dictionary-based and linear computational models
• Nonlinear approximation via compositions
• Publication:4943029
• Adaptive greedy approximations
• Geometric Upper Bounds on Rates of Variable-Basis Approximation

Cites work

• scientific article; zbMATH DE number 3126094 (Why is no real title available?)
• scientific article; zbMATH DE number 3877692 (Why is no real title available?)
• scientific article; zbMATH DE number 3772326 (Why is no real title available?)
• scientific article; zbMATH DE number 1182753 (Why is no real title available?)
• scientific article; zbMATH DE number 3337815 (Why is no real title available?)
• A Sobolev-type upper bound for rates of approximation by linear combinations of Heaviside plane waves
• A simple lemma on greedy approximation in Hilbert space and convergence rates for projection pursuit regression and neural network training
• Accuracy of suboptimal solutions to kernel principal component analysis
• Approximate minimization of the regularized expected error over kernel models
• Approximating networks and extended Ritz method for the solution of functional optimization problems
• Approximation schemes for functional optimization problems
• Bounds on rates of variable-basis and neural-network approximation
• Comparison of worst case errors in linear and neural network approximation
• Complexity of Gaussian-radial-basis networks approximating smooth functions
• Geometric Upper Bounds on Rates of Variable-Basis Approximation
• On the exponential convergence of matching pursuits in quasi-incoherent dictionaries
• Optimization of approximating networks for optimal fault diagnosis
• Regularization techniques and suboptimal solutions to optimization problems in learning from data
• Universal approximation bounds for superpositions of a sigmoidal function

Cited in

(5)

• 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
• Probabilistic lower bounds for approximation by shallow perceptron networks
• Some comparisons of complexity in dictionary-based and linear computational models
• Correlations of random classifiers on large data sets

This page was built for publication: Can dictionary-based computational models outperform the best linear ones?

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q456017)