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

DOI10.1016/j.neunet.2011.05.014zbMath1250.68223OpenAlexW1967629633WikidataQ51554247 ScholiaQ51554247MaRDI QIDQ456017

Marcello Sanguineti, Giorgio Gnecco, Vera Kurková

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 approximationrates of approximationworst-case errorKolmogorov widthdictionary-based approximationperceptron networks

Mathematics Subject Classification ID

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

Related Items (4)

Probabilistic lower bounds for approximation by shallow perceptron 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 ⋮ Correlations of random classifiers on large data sets

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Accuracy of suboptimal solutions to kernel principal component analysis
• 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
• A Sobolev-type upper bound for rates of approximation by linear combinations of Heaviside plane waves
• Approximate Minimization of the Regularized Expected Error over Kernel Models
• On the exponential convergence of matching pursuits in quasi-incoherent dictionaries
• Regularization Techniques and Suboptimal Solutions to Optimization Problems in Learning from Data
• Geometric Upper Bounds on Rates of Variable-Basis Approximation
• Universal approximation bounds for superpositions of a sigmoidal function
• Bounds on rates of variable-basis and neural-network approximation
• Comparison of worst case errors in linear and neural network approximation
• Optimization of approximating networks for optimal fault diagnosis
• Approximating networks and extended Ritz method for the solution of functional optimization problems

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