Generalization error of combined classifiers.

DOI10.1006/jcss.2002.1854zbMath1059.68093OpenAlexW2080984025MaRDI QIDQ1872713

Mostefa Golea, Llew Mason, Bartlett, Peter L.

Publication date: 14 May 2003

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

Full work available at URL: https://semanticscholar.org/paper/d2219fb29c1fa4d3bca7d2cb68da32ffe2ce17ef

zbMATH Keywords

neural networksdecision treesvoting methodsmargins analysisboosting.

Mathematics Subject Classification ID

Learning and adaptive systems in artificial intelligence (68T05) Pattern recognition, speech recognition (68T10)

Related Items

Analysis of the generalization ability of a full decision tree ⋮ Optimal third root asymptotic bounds in the statistical estimation of thresholds

Uses Software

• AdaBoost.MH

Cites Work

• Unnamed Item
• Bagging predictors
• A result of Vapnik with applications
• A decision-theoretic generalization of on-line learning and an application to boosting
• Arcing classifiers. (With discussion)
• Boosting the margin: a new explanation for the effectiveness of voting methods
• On the density of families of sets
• The sample complexity of pattern classification with neural networks: the size of the weights is more important than the size of the network
• Probability Inequalities for Sums of Bounded Random Variables
• On the Uniform Convergence of Relative Frequencies of Events to Their Probabilities