The Power of Vacillation in Language Learning

DOI10.1137/S0097539793249694zbMath0939.68099OpenAlexW2002485318MaRDI QIDQ4268851

John Case

Publication date: 28 October 1999

Published in: SIAM Journal on Computing (Search for Journal in Brave)

Full work available at URL: https://doi.org/10.1137/s0097539793249694

zbMATH Keywords

computational learning theorytopologylanguage learningrecursion theoryinductive reference

Mathematics Subject Classification ID

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

Related Items (42)

Intrinsic complexity of learning geometrical concepts from positive data ⋮ Effectivity Questions for Kleene’s Recursion Theorem ⋮ Learnability: Admissible, co-finite, and hypersimple languages ⋮ Learning in the presence of inaccurate information ⋮ Effectivity questions for Kleene's recursion theorem ⋮ Results on memory-limited U-shaped learning ⋮ Strongly non-U-shaped language learning results by general techniques ⋮ Infinitary self-reference in learning theory ⋮ On aggregating teams of learning machines ⋮ Prudence in vacillatory language identification ⋮ Learning theory in the arithmetic hierarchy. II. ⋮ Computability-theoretic learning complexity ⋮ Machine induction without revolutionary paradigm shifts ⋮ Gold-Style Learning Theory ⋮ Uncountable automatic classes and learning ⋮ Prescribed Learning of R.E. Classes ⋮ Learning in Friedberg Numberings ⋮ Numberings Optimal for Learning ⋮ When unlearning helps ⋮ Learning by switching type of information. ⋮ Non-U-shaped vacillatory and team learning ⋮ Learnability and positive equivalence relations ⋮ Learning in Friedberg numberings ⋮ On the non-existence of maximal inference degrees for language identification ⋮ Learnability of automatic classes ⋮ Numberings optimal for learning ⋮ Hypothesis spaces for learning ⋮ Synthesizing learners tolerating computable noisy data ⋮ Vacillatory and BC learning on noisy data ⋮ Variations on U-shaped learning ⋮ Learnability and positive equivalence relations ⋮ Topological separations in inductive inference ⋮ Resource restricted computability theoretic learning: Illustrative topics and problems ⋮ Hypothesis Spaces for Learning ⋮ U-shaped, iterative, and iterative-with-counter learning ⋮ Learning correction grammars ⋮ Prescribed learning of r.e. classes ⋮ Uncountable Automatic Classes and Learning ⋮ Maximal machine learnable classes ⋮ The synthesis of language learners. ⋮ Incremental concept learning for bounded data mining. ⋮ On the role of update constraints and text-types in iterative learning

This page was built for publication: The Power of Vacillation in Language Learning