Approximation of classifiers by deep perceptron networks

DOI10.1016/J.NEUNET.2023.06.004MaRDI QIDQ6488832zbMATH OpenFDO

Authors Věra Kůrková, Marcello Sanguineti

Publication date 26 October 2023

Published in Neural Networks (Search for Journal in Brave)

Full work available at URL https://doi.org/10.1016/J.NEUNET.2023.06.004

zbMATH Keywords

approximation by deep networksconcentration of measuregrowth functionsmethod of bounded differencesprobabilistic bounds on approximation errorsrandom classifiers

Mathematics Subject Classification ID

Approximations and expansions (41-XX) Statistics (62-XX) Artificial neural networks and deep learning (68T07)

Recommendations

• Deep Neural Network Approximation Theory
• Approximation spaces of deep neural networks
• scientific article; zbMATH DE number 3963219
• Approximation by neural networks and learning theory
• Approximation properties of deep ReLU CNNs
• Deep vs. shallow networks: an approximation theory perspective
• Provable approximation properties for deep neural networks
• Approximation capabilities of neural networks
• Probabilistic lower bounds for approximation by shallow perceptron networks

Cites work

• Approximation bounds for random neural networks and reservoir systems
• Approximation with random bases: pro et contra
• Asymptotic theory of finite dimensional normed spaces. With an appendix by M. Gromov: Isoperimetric inequalities in Riemannian manifolds
• Blessing of dimensionality: mathematical foundations of the statistical physics of data
• Bounding the Vapnik-Chervonenkis dimension of concept classes parameterized by real numbers
• Concentration of Measure for the Analysis of Randomized Algorithms
• Correction of AI systems by linear discriminants: probabilistic foundations
• Correlations of random classifiers on large data sets
• Dependence of Computational Models on Input Dimension: Tractability of Approximation and Optimization Tasks
• Enumeration of Seven-Argument Threshold Functions
• Error bounds for approximations with deep ReLU networks
• scientific article; zbMATH DE number 3126094 (Why is no real title available?)
• scientific article; zbMATH DE number 109318 (Why is no real title available?)
• scientific article; zbMATH DE number 1182755 (Why is no real title available?)
• scientific article; zbMATH DE number 1749054 (Why is no real title available?)
• scientific article; zbMATH DE number 7064043 (Why is no real title available?)
• Observed universality of phase transitions in high-dimensional geometry, with implications for modern data analysis and signal processing
• On best approximation by ridge functions
• On the Uniform Convergence of Relative Frequencies of Events to Their Probabilities
• Probabilistic lower bounds for approximation by shallow perceptron networks

Cited in

(3)

• The asymptotic optimization of pre-edited ANN classifier
• Probabilistic lower bounds for approximation by shallow perceptron networks
• Concentration of measure and global optimization of Bayesian multilayer perceptron. I

This page was built for publication: Approximation of classifiers by deep perceptron networks

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6488832)