Parallelism increases iterative learning power

DOI10.1016/j.tcs.2009.01.015zbMath1167.68024OpenAlexW2175108584MaRDI QIDQ1017664

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

computational learning theoryparallelisminductive inferencelanguage learningiterative learningparallel learningGold-style learningmemory limited learning

Mathematics Subject Classification ID

Computational learning theory (68Q32)

Related Items (3)

Strongly non-U-shaped language learning results by general techniques ⋮ Iterative learning of simple external contextual languages ⋮ Towards a map for incremental learning in the limit from positive and negative information

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• A machine discovery from amino acid sequences by decision trees over regular patterns
• Polynomial-time inference of arbitrary pattern languages
• U-shaped, iterative, and iterative-with-counter learning
• Finding patterns common to a set of strings
• Incremental learning from positive data
• Incremental concept learning for bounded data mining.
• Language learning from texts: Mindchanges, limited memory and monotonicity
• Results on memory-limited U-shaped learning
• Parallelism Increases Iterative Learning Power
• Learning Left-to-Right and Right-to-Left Iterative Languages
• Periodicity in generations of automata
• Infinitary self-reference in learning theory
• Language identification in the limit
• Predictive learning models for concept drift

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