Set-driven and rearrangement-independent learning of recursive languages

DOI10.1007/BF01301967zbMath0860.68088MaRDI QIDQ4717054

Thomas Zeugmann, Steffen Lange

Publication date: 1 December 1996

Published in: Mathematical Systems Theory (Search for Journal in Brave)

zbMATH Keywords

conservative learninglearnabilityuniformly recursive languages

Mathematics Subject Classification ID

Learning and adaptive systems in artificial intelligence (68T05) Formal languages and automata (68Q45)

Related Items (15)

Generalized notions of mind change complexity ⋮ From learning in the limit to stochastic finite learning ⋮ Probabilistic language learning under monotonicity constraints ⋮ Learning indexed families of recursive languages from positive data: A survey ⋮ Monotonic and dual monotonic language learning ⋮ Hypothesis spaces for learning ⋮ Learning one-variable pattern languages very efficiently on average, in parallel, and by asking queries ⋮ Hypothesis Spaces for Learning ⋮ U-shaped, iterative, and iterative-with-counter learning ⋮ Algorithms for learning regular expressions from positive data ⋮ An average-case optimal one-variable pattern language learner ⋮ Incremental concept learning for bounded data mining. ⋮ Inductive inference of approximations for recursive concepts ⋮ Variants of iterative learning ⋮ Mapping monotonic restrictions in inductive inference

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Monotonic and dual monotonic language learning
• Monotonic and non-monotonic inductive inference
• Polynomial-time inference of arbitrary pattern languages
• Prudence and other conditions on formal language learning
• Finding patterns common to a set of strings
• Lange and Wiehagen's pattern language learning algorithm: An average-case analysis with respect to its total learning time
• Inductive inference of formal languages from positive data
• Toward a mathematical theory of inductive inference
• LEARNING RECURSIVE LANGUAGES WITH BOUNDED MIND CHANGES
• Characterization of language learning front informant under various monotonicity constraints
• Ignoring data may be the only way to learn efficiently
• Language identification in the limit

This page was built for publication: Set-driven and rearrangement-independent learning of recursive languages