Bounding sample size with the Vapnik-Chervonenkis dimension

DOI10.1016/0166-218X(93)90179-RMaRDI QIDQ1209149zbMATH OpenFDO

Authors John Shawe-Taylor, Martin Anthony, Norman L. Biggs

Publication date 16 May 1993

Published in Discrete Applied Mathematics (Search for Journal in Brave)

zbMATH Keywords

Vapnik-Chervonenkis dimensionP.A.C

Mathematics Subject Classification ID

Learning and adaptive systems in artificial intelligence (68T05)

Recommendations

• Learning faster than promised by the Vapnik-Chervonenkis dimension
• Results on learnability and the Vapnik-Chervonenkis dimension
• Learnability and the Vapnik-Chervonenkis dimension
• A result of Vapnik with applications
• Bounding the Vapnik-Chervonenkis dimension of concept classes parameterized by real numbers

Cites work

• A theory of the learnable
• Computational limitations on learning from examples
• Learnability and the Vapnik-Chervonenkis dimension
• On the Uniform Convergence of Relative Frequencies of Events to Their Probabilities
• Quantifying inductive bias: AI learning algorithms and Valiant's learning framework
• -nets and simplex range queries

Cited in

(11)

• PAC-learning from general examples
• Learning faster than promised by the Vapnik-Chervonenkis dimension
• Using the doubling dimension to analyze the generalization of learning algorithms
• Learning with side information: PAC learning bounds
• An approach to guided learning of Boolean functions
• The optimal sample complexity of PAC learning
• A generalization of Sauer's lemma
• Combinatorics and connectionism
• A result of Vapnik with applications
• Improved bounds on the sample complexity of learning
• Valid Generalisation from Approximate Interpolation

This page was built for publication: Bounding sample size with the Vapnik-Chervonenkis dimension

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q1209149)