GEOMETRIC ERGODICITY OF THE NORMALIZED PERCEPTRON ALGORITHM FOR THE CLASSIFICATION OF NON-SEPARABLE GAUSSIAN INPUT VECTORS

DOI10.17654/ADASJul2015_037_055zbMath1345.60072MaRDI QIDQ2795840

Rieken S. Venema

Publication date: 22 March 2016

Published in: Advances and Applications in Statistics (Search for Journal in Brave)

Full work available at URL: http://www.pphmj.com/abstract/9331.htm

zbMATH Keywords

Markov chains; geometric ergodicity; single-layer perceptron; non-separable classifications; normalized perceptron algorithm

Mathematics Subject Classification ID

62G20: Asymptotic properties of nonparametric inference

60J05: Discrete-time Markov processes on general state spaces

62M45: Neural nets and related approaches to inference from stochastic processes