Automatic pattern recognition: a study of the probability of error

DOI10.1109/34.3915zbMath0661.62056OpenAlexW2071223680MaRDI QIDQ3810712

Luc P. Devroye

Publication date: 1988

Published in: IEEE Transactions on Pattern Analysis and Machine Intelligence (Search for Journal in Brave)

Full work available at URL: https://semanticscholar.org/paper/e85a68602abf92fcc1efb8b7aa90d27d141a80c2

zbMATH Keywords

consistencyerror estimationstatistical pattern recognitionasymptotic optimalityprobability of errortest sequencesmoothing parameterempirical risktraining sequencek-nearest neighbor ruleautomatic parameter selectiondiscrimination rulesDistribution free boundskernel-based rulesVapnik-Chernovenkis inequality

Mathematics Subject Classification ID

Classification and discrimination; cluster analysis (statistical aspects) (62H30)

Related Items (11)

A theory for memory-based learning ⋮ A counterexample concerning uniform ergodic theorems for a class of functions ⋮ Classification by polynomial surfaces ⋮ A consistent combined classification rule ⋮ Decision theoretic generalizations of the PAC model for neural net and other learning applications ⋮ Classifier selection from a totally bounded class of functions ⋮ An iterated classification rule based on auxiliary pseudo-predictors. ⋮ Theory of Classification: a Survey of Some Recent Advances ⋮ Consistency of data-driven histogram methods for density estimation and classification ⋮ Histogram regression estimation using data-dependent partitions ⋮ A kernel-based combined classification rule

This page was built for publication: Automatic pattern recognition: a study of the probability of error