Learning recursive functions from approximations

DOI10.1006/jcss.1997.1508zbMath0880.68107OpenAlexW1980411366MaRDI QIDQ1370868

Susanne Kaufmann, John Case, Martin Kummer, E. B. Kinber

Publication date: 2 February 1998

Published in: Journal of Computer and System Sciences (Search for Journal in Brave)

Full work available at URL: https://doi.org/10.1006/jcss.1997.1508

zbMATH Keywords

algorithmic learningfrequency computations

Mathematics Subject Classification ID

Learning and adaptive systems in artificial intelligence (68T05)

Related Items (7)

Trees and learning ⋮ The power of frequency computation ⋮ On the Influence of Technology on Learning Processes ⋮ Robust learning with infinite additional information ⋮ The synthesis of language learners. ⋮ Learning to win process-control games watching game-masters ⋮ Avoiding coding tricks by hyperrobust learning

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Comparison of identification criteria for machine inductive inference
• Training sequences
• Polynomial terse sets
• Program size, oracles, and the jump operation
• Classical recursion theory. Vol. II
• Extremes in the degrees of inferability
• Terse, superterse, and verbose sets
• Quantifying the amount of verboseness
• Approximable sets
• Inclusion problems in parallel learning and games
• Learnability and the Vapnik-Chervonenkis dimension
• Probabilistic inductive inference
• The Power of Pluralism for Automatic Program Synthesis
• A proof of Beigel's cardinality conjecture
• Learning via queries
• Inductive inference of recursive functions: Qualitative theory
• A cardinality version of Beigel's nonspeedup theorem
• The power of frequency computation
• A variant of the Kolmogorov concept of complexity

This page was built for publication: Learning recursive functions from approximations