Parallelism increases iterative learning power

DOI10.1016/J.TCS.2009.01.015MaRDI QIDQ1017664zbMATH OpenOpenAlexFDO

Authors John Case, Samuel E. III Moelius

Publication date 12 May 2009

Published in Theoretical Computer Science (Search for Journal in Brave)

Full work available at URL https://doi.org/10.1016/j.tcs.2009.01.015

zbMATH Keywords

inductive inferenceiterative learningparallelismcomputational learning theorylanguage learningparallel learningGold-style learningmemory limited learning

Mathematics Subject Classification ID

Computational learning theory (68Q32)

Recommendations

• Parallelism Increases Iterative Learning Power
• Variants of iterative learning
• Parallel learning of automatic classes of languages
• Iterative Learning from Positive Data and Counters
• Iterative learning from positive data and counters

Cites work

• scientific article; zbMATH DE number 439891 (Why is no real title available?)
• scientific article; zbMATH DE number 3817068 (Why is no real title available?)
• scientific article; zbMATH DE number 3932417 (Why is no real title available?)
• scientific article; zbMATH DE number 67629 (Why is no real title available?)
• scientific article; zbMATH DE number 3539202 (Why is no real title available?)
• scientific article; zbMATH DE number 2077161 (Why is no real title available?)
• scientific article; zbMATH DE number 743586 (Why is no real title available?)
• scientific article; zbMATH DE number 3291134 (Why is no real title available?)
• A machine discovery from amino acid sequences by decision trees over regular patterns
• Finding patterns common to a set of strings
• Incremental concept learning for bounded data mining.
• Incremental learning from positive data
• Infinitary self-reference in learning theory
• Language identification in the limit
• Language learning from texts: Mindchanges, limited memory and monotonicity
• Learning Left-to-Right and Right-to-Left Iterative Languages
• Parallelism Increases Iterative Learning Power
• Periodicity in generations of automata
• Polynomial-time inference of arbitrary pattern languages
• Predictive learning models for concept drift
• Results on memory-limited U-shaped learning
• U-shaped, iterative, and iterative-with-counter learning

Cited in

(5)

• Parallelism Increases Iterative Learning Power
• Iterative learning of simple external contextual languages
• Widening: using parallel resources to improve model quality
• Strongly non-U-shaped language learning results by general techniques
• Towards a map for incremental learning in the limit from positive and negative information

This page was built for publication: Parallelism increases iterative learning power

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q1017664)