Knowing what doesn't matter: exploiting the omission of irrelevant data

DOI10.1016/S0004-3702(97)00048-9MaRDI QIDQ1127363zbMATH OpenFDO

Authors Russell Greiner, Adam J. Grove, Alex Kogan

Publication date 13 August 1998

Published in Artificial Intelligence (Search for Journal in Brave)

Full work available at URL https://doi.org/10.1016/S0004-3702(97)00048-9

zbMATH Keywords

adversarial noiseblocked attributesdecision treesdiagnosisDNFirrelevant valueslearnabilitytheory revision

Mathematics Subject Classification ID

Learning and adaptive systems in artificial intelligence (68T05) Parallel algorithms in computer science (68W10)

Recommendations

• Partial observability and learnability
• Learning from examples with unspecified attribute values.
• scientific article; zbMATH DE number 2086401
• How many missing answers can be tolerated by query learners?
• Learning in the presence of finitely or infinitely many irrelevant attributes

Cites work

• A Measure of Asymptotic Efficiency for Tests of a Hypothesis Based on the sum of Observations
• A theory of the learnable
• Can PAC learning algorithms tolerate random attribute noise?
• Equivalence of models for polynomial learnability
• scientific article; zbMATH DE number 3860199 (Why is no real title available?)
• scientific article; zbMATH DE number 4088699 (Why is no real title available?)
• scientific article; zbMATH DE number 50693 (Why is no real title available?)
• Knowing what doesn't matter: exploiting the omission of irrelevant data
• Learning Boolean functions in an infinite attribute space
• Learning decision trees from random examples
• Learning in the presence of finitely or infinitely many irrelevant attributes
• Learning in the Presence of Malicious Errors
• On the learnability of discrete distributions
• Teaching a smarter learner.
• The complexity of theory revision

Cited in

(8)

• Selection of relevant features and examples in machine learning
• Knowing what doesn't matter: exploiting the omission of irrelevant data
• The complexity of theory revision
• Logical analysis of binary data with missing bits
• Information-theoretic approaches to SVM feature selection for metagenome read classification
• Learning cost-sensitive active classifiers
• Ignoring data may be the only way to learn efficiently
• Partial observability and learnability

Describes a project that uses

Uses Software

• C4.5

This page was built for publication: Knowing what doesn't matter: exploiting the omission of irrelevant data

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q1127363)