Worst-case analysis of the Perceptron and Exponentiated Update algorithms

DOI10.1016/S0004-3702(98)00098-8MaRDI QIDQ1277700zbMATH OpenFDO

Authors Tom Bylander

Publication date 2 March 1999

Published in Artificial Intelligence (Search for Journal in Brave)

Full work available at URL https://doi.org/10.1016/S0004-3702(98)00098-8

zbMATH Keywords

absolute loss boundslearning algorithmsmistake boundsrandomized classification algorithms

Mathematics Subject Classification ID

Learning and adaptive systems in artificial intelligence (68T05)

Recommendations

• The Perceptron algorithm versus Winnow: linear versus logarithmic mistake bounds when few input variables are relevant
• Learning Theory
• General convergence results for linear discriminant updates
• How to better use expert advice

Cites work

• A polynomial-time algorithm for learning noisy linear threshold functions
• Exponentiated gradient versus gradient descent for linear predictors
• scientific article; zbMATH DE number 1306864 (Why is no real title available?)
• scientific article; zbMATH DE number 3436645 (Why is no real title available?)
• scientific article; zbMATH DE number 3438431 (Why is no real title available?)
• scientific article; zbMATH DE number 3231758 (Why is no real title available?)
• scientific article; zbMATH DE number 3285265 (Why is no real title available?)
• scientific article; zbMATH DE number 3314813 (Why is no real title available?)
• scientific article; zbMATH DE number 3189712 (Why is no real title available?)
• Probability Inequalities for Sums of Bounded Random Variables
• The Perceptron: A Model for Brain Functioning. I
• The weighted majority algorithm
• Tracking the best expert

Cited in

(2)

• Learning to assign degrees of belief in relational domains
• Learning DNF in time \(2^{\widetilde O(n^{1/3})}\)

This page was built for publication: Worst-case analysis of the Perceptron and Exponentiated Update algorithms

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q1277700)