Devroye, Luc; Györfi, László; Lugosi, Gábor A probabilistic theory of pattern recognition. (English) Zbl 0853.68150 Applications of Mathematics. 31. New York, NY: Springer. xv, 636 p. (1996). Non-parametric estimators and bounds for classification rules, \(k\)-nearest neighbor rules, and their consistency; error estimation – Vapnik-Chervonenkis theory about convergence for all data distributions; shatter coefficients and generalized linear discriminants, parametric classification. Tree classifies, BSP trees and splitting criteria. Data dependent partitioning, and resubstitution estimator. Potential kernel functions, automatic kernels and nearest neighbor rules. Neural network classifiers, Hypercube classifiers, Hypercube classifiers, Problems and exercises attached to each chapter. Reviewer: L.F.Pau (Alvsjo) Cited in 2 ReviewsCited in 391 Documents MSC: 68T10 Pattern recognition, speech recognition 68-02 Research exposition (monographs, survey articles) pertaining to computer science Keywords:potential kernel functions; neural network; hypercube; BSP trees PDF BibTeX XML Cite \textit{L. Devroye} et al., A probabilistic theory of pattern recognition. New York, NY: Springer (1996; Zbl 0853.68150)