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

DOI10.1016/S0004-3702(97)00048-9zbMath0904.68141MaRDI QIDQ1127363

Alexander Kogan, Russell Greiner, Adam J. Grove

Publication date: 13 August 1998

Published in: Artificial Intelligence (Search for Journal in Brave)

zbMATH Keywords

decision treesdiagnosistheory revisionDNFlearnabilityadversarial noiseblocked attributesirrelevant values

Mathematics Subject Classification ID

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

Related Items

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

Uses Software

• C4.5

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• Teaching a smarter learner.
• Knowing what doesn't matter: exploiting the omission of irrelevant data
• Equivalence of models for polynomial learnability
• Learning Boolean functions in an infinite attribute space
• The complexity of theory revision
• Learning decision trees from random examples
• Learning in the presence of finitely or infinitely many irrelevant attributes
• Can PAC learning algorithms tolerate random attribute noise?
• On the learnability of discrete distributions
• Learning in the Presence of Malicious Errors
• A theory of the learnable
• A Measure of Asymptotic Efficiency for Tests of a Hypothesis Based on the sum of Observations