Perceptron, Winnow, and PAC Learning

DOI10.1137/S0097539798340928zbMATH Open1051.68084MaRDI QIDQ3149871FDOQ3149871

Authors: Rocco A. Servedio 

Publication date: 29 September 2002

Published in: SIAM Journal on Computing (Search for Journal in Brave)

Recommendations

• PAC analogues of Perceptron and Winnow via boosting the margin
• The Perceptron algorithm versus Winnow: linear versus logarithmic mistake bounds when few input variables are relevant
• Learning binary perceptrons perfectly efficiently.
• 10.1162/1532443041424274
• scientific article; zbMATH DE number 2089359

zbMATH Keywords

PAC learningPerceptronWinnowlinear threshold function

Mathematics Subject Classification ID

Computational learning theory (68Q32)

Cited In (10)

• A simple polynomial-time rescaling algorithm for solving linear programs
• Learning binary perceptrons perfectly efficiently.
• An empirical comparison for the performance of single-layer algorithms for training threshold logic units
• Some notes on perceptron learning
• General convergence results for linear discriminant updates
• On the perceptron learning algorithm on data with high precision
• Perceptron algorithms for the classification of non-separable populations
• PAC analogues of Perceptron and Winnow via boosting the margin
• Using the Perceptron Algorithm to Find Consistent Hypotheses
• Minimum generalization via reflection: A fast linear threshold learner

This page was built for publication: Perceptron, Winnow, and PAC Learning

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q3149871)