On the perceptron learning algorithm on data with high precision

DOI10.1016/S0022-0000(05)80008-XMaRDI QIDQ1329165zbMATH OpenFDO

Authors Kai-Yeung Siu, Amir Dembo, T. Kailath

Publication date 9 October 1995

Published in Journal of Computer and System Sciences (Search for Journal in Brave)

Full work available at URL https://doi.org/10.1016/S0022-0000(05)80008-X

zbMATH Keywords

random matricesperceptron algorithm

Mathematics Subject Classification ID

Learning and adaptive systems in artificial intelligence (68T05)

Recommendations

• scientific article; zbMATH DE number 529787
• Learning Theory
• Some notes on perceptron learning
• scientific article; zbMATH DE number 3963219
• Perceptron, Winnow, and PAC Learning
• Learning binary perceptrons perfectly efficiently.
• On the convergence of the Albus Perceptron
• The Perceptron algorithm versus Winnow: linear versus logarithmic mistake bounds when few input variables are relevant
• Learning of higher-order perceptrons with tunable complexities

Cites work

• scientific article; zbMATH DE number 46318 (Why is no real title available?)
• scientific article; zbMATH DE number 3892457 (Why is no real title available?)
• scientific article; zbMATH DE number 3231758 (Why is no real title available?)
• scientific article; zbMATH DE number 3245540 (Why is no real title available?)
• A new polynomial-time algorithm for linear programming
• Enumeration of Seven-Argument Threshold Functions
• Limit of the smallest eigenvalue of a large dimensional sample covariance matrix
• On random determinants
• Random polytopes in the d-dimensional cube

Cited in

(10)

• Learning Theory
• Capacity of the covariance perceptron
• scientific article; zbMATH DE number 1827089 (Why is no real title available?)
• scientific article; zbMATH DE number 3963219 (Why is no real title available?)
• scientific article; zbMATH DE number 529787 (Why is no real title available?)
• Geometric ergodicity of the normalized perceptron algorithm for the classification of non-separable Gaussian input vectors
• Probabilistic analysis of a learning matrix
• Tractability from overparametrization: the example of the negative perceptron
• A deterministic and polynomial modified perceptron algorithm
• A polynomial training algorithm for calculating perceptrons of optimal stability

This page was built for publication: On the perceptron learning algorithm on data with high precision

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q1329165)