Strong universal consistency of neural network classifiers

DOI10.1109/18.243433MaRDI QIDQ4307316zbMATH OpenOpenAlexFDO

Authors Andras Farago, Gábor Lugosi

Publication date 4 October 1994

Published in IEEE Transactions on Information Theory (Search for Journal in Brave)

Full work available at URL https://doi.org/10.1109/18.243433

zbMATH Keywords

statistical pattern recognitionuniversally consistent classifiers

Mathematics Subject Classification ID

Learning and adaptive systems in artificial intelligence (68T05) Pattern recognition, speech recognition (68T10)

Recommendations

• Universal Consistency of Deep Convolutional Neural Networks
• The strong consistency of error probability estimates in nn discrimination
• Universality of deep convolutional neural networks
• Universality of gradient descent neural network training
• scientific article; zbMATH DE number 1735798
• Robustness of representations in multilayer feedforward neural networks
• Stability for the training of deep neural networks and other classifiers
• Universal approximation theorem for interval neural networks

Cited in

(16)

• Hardness results for neural network approximation problems
• Classifier performance as a function of distributional complexity
• A counterexample concerning uniform ergodic theorems for a class of functions
• Correlations of random classifiers on large data sets
• A deep learning semiparametric regression for adjusting complex confounding structures
• A nonparametric ensemble binary classifier and its statistical properties
• On extension theorems and their connection to universal consistency in machine learning
• scientific article; zbMATH DE number 1203217 (Why is no real title available?)
• Learning and Convergence of the Normalized Radial Basis Functions Networks
• Universal consistency of Wasserstein k-NN classifier: a negative and some positive results
• Deep learning from a statistical perspective
• Piecewise integrable neural network: an interpretable chaos identification framework
• Causal deep learning: encouraging impact on real-world problems through causality
• A deep neural network two-part model and feature importance test for semicontinuous data
• Extrapolation of the Bayesian classifier with an unknown support of the two-class mixture distribution
• Functional classification of ornamental stone using machine learning techniques

This page was built for publication: Strong universal consistency of neural network classifiers

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q4307316)