Synthesizing noise-tolerant language learners

DOI10.1016/S0304-3975(00)00132-8zbMath0973.68091OpenAlexW2180498019MaRDI QIDQ5941367

John Case, Arun Sharma, Sanjay Jain

Publication date: 20 August 2001

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

Full work available at URL: https://doi.org/10.1016/s0304-3975(00)00132-8

zbMATH Keywords

families of languagesnoise-tolerant language-learnersr.e. classes

Mathematics Subject Classification ID

Computational learning theory (68Q32)

Related Items (4)

Learning indexed families of recursive languages from positive data: A survey ⋮ Synthesizing learners tolerating computable noisy data ⋮ On the power of incremental learning. ⋮ The synthesis of language learners.

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Comparison of identification criteria for machine inductive inference
• Monotonic and dual monotonic language learning
• Characterizing language identification in terms of computable numberings
• Synthesizing inductive expertise
• Classical recursion theory. Vol. II
• Characterizing language identification by standardizing operations
• Characterizations of monotonic and dual monotonic language learning
• Robust separations in inductive inference
• Inductive inference of formal languages from positive data
• Periodicity in generations of automata
• Toward a mathematical theory of inductive inference
• Infinitary self-reference in learning theory
• Language learning without overgeneralization
• A Machine-Independent Theory of the Complexity of Recursive Functions
• Language identification in the limit
• Vacillatory and BC learning on noisy data

This page was built for publication: Synthesizing noise-tolerant language learners