Perceptron algorithms for the classification of non-separable populations

DOI10.1080/15326349708807422MaRDI QIDQ4340649zbMATH OpenOpenAlexFDO

Authors Rienk Venema, Robert Burton, Herold Dehling

Publication date 7 January 1998

Published in Communications in Statistics. Stochastic Models (Search for Journal in Brave)

Full work available at URL https://doi.org/10.1080/15326349708807422

zbMATH Keywords

ergodicitylearningMarkov chainsnonseparable classificationsperceptron algorithm

Mathematics Subject Classification ID

Applications of Markov chains and discrete-time Markov processes on general state spaces (social mobility, learning theory, industrial processes, etc.) (60J20) Neural nets applied to problems in time-dependent statistical mechanics (82C32)

Recommendations

• Algorithm of neural classification by observations from a mixture with variable concentrations
• scientific article; zbMATH DE number 3963219
• Learning nondeterministic classifiers
• scientific article; zbMATH DE number 778112
• Perceptron, Winnow, and PAC Learning
• scientific article; zbMATH DE number 3204224
• scientific article; zbMATH DE number 815425

Cited in

(7)

• New methods for testing linear separability
• An empirical comparison for the performance of single-layer algorithms for training threshold logic units
• Geometric ergodicity of the normalized perceptron algorithm for the classification of non-separable Gaussian input vectors
• Using the Perceptron Algorithm to Find Consistent Hypotheses
• scientific article; zbMATH DE number 2044685 (Why is no real title available?)
• scientific article; zbMATH DE number 822102 (Why is no real title available?)
• Learning perceptrons and piecewise linear classifiers sensitive to example dependent costs

This page was built for publication: Perceptron algorithms for the classification of non-separable populations

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q4340649)