Correlations of random classifiers on large data sets

DOI10.1007/S00500-021-05938-4MaRDI QIDQ2100403zbMATH OpenOpenAlexFDO

Authors Marcello Sanguineti, Věra Kůrková

Publication date 22 November 2022

Published in Soft Computing (Search for Journal in Brave)

Full work available at URL https://doi.org/10.1007/s00500-021-05938-4

zbMATH Keywords

binary classificationconcentration of measuremethod of bounded differencesoptimization of feedforward networksrandom classifiers

Mathematics Subject Classification ID

Learning and adaptive systems in artificial intelligence (68T05) Computational aspects of data analysis and big data (68T09)

Recommendations

• Analysis of a classifier with random thresholds
• Correlation of internal representations in feed-forward neural networks
• Estimates of Data Complexity in Neural-Network Learning
• The sample complexity of pattern classification with neural networks: the size of the weights is more important than the size of the network
• Strong universal consistency of neural network classifiers

Cites work

• Approximation error bounds via Rademacher's complexity
• Approximation with random bases: pro et contra
• Can dictionary-based computational models outperform the best linear ones?
• Complexity estimates based on integral transforms induced by computational units
• Concentration Inequalities and Martingale Inequalities: A Survey
• Concentration of Measure for the Analysis of Randomized Algorithms
• Dependence of Computational Models on Input Dimension: Tractability of Approximation and Optimization Tasks
• Greed is Good: Algorithmic Results for Sparse Approximation
• 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 1749054 (Why is no real title available?)
• Minimization of Error Functionals over Variable-Basis Functions
• On a Variational Norm Tailored to Variable-Basis Approximation Schemes
• On the tractability of multivariate integration and approximation by neural networks
• Probabilistic lower bounds for approximation by shallow perceptron networks
• Quasiorthogonal dimension
• Quasiorthogonal dimension of Euclidean spaces
• Some comparisons of complexity in dictionary-based and linear computational models
• Universal approximation bounds for superpositions of a sigmoidal function
• Weighted sums of certain dependent random variables

Cited in

(4)

• Random Databases with Correlated Data
• Exact Density of W Classification Statistic Based on Unmatched Training Sample from Correlated Populations
• scientific article; zbMATH DE number 2044185 (Why is no real title available?)
• Approximation of classifiers by deep perceptron networks

This page was built for publication: Correlations of random classifiers on large data sets

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q2100403)