Characterizing language identification in terms of computable numberings
Inductive inference is concerned with machines that infer (or learn) the index for a computable function (or r.e. set) from information about that function. The usual model involves getting function values and making conjectures about what the function might be. The conjectures may change over time. There are two very different threads: learning recursive functions from \(f(0),f(1),\ldots\), and learning r.e. sets from just seeing elements that are in the set. Freivalds characterized exactly what classes of functions could be learned in terms of computable numberings. This paper does a similar characterization for learning classes of r.e. sets.
- Characterizing language identification by standardizing operations
- The intrinsic complexity of language identification
- Investigations on measure-one identification of classes of languages
- scientific article; zbMATH DE number 67629
- On the non-existence of maximal inference degrees for language identification
- Identification in the Limit of Systematic-Noisy Languages
- On counting functions of languages
- Characterizing language identification by standardizing operations
- CONNECTIONS BETWEEN IDENTIFYING FUNCTIONALS, STANDARDIZING OPERATIONS, AND COMPUTABLE NUMBERINGS
- Gödel numberings of partial recursive functions
- scientific article; zbMATH DE number 996382 (Why is no real title available?)
- scientific article; zbMATH DE number 3932417 (Why is no real title available?)
- scientific article; zbMATH DE number 3681743 (Why is no real title available?)
- scientific article; zbMATH DE number 1351096 (Why is no real title available?)
- scientific article; zbMATH DE number 1351107 (Why is no real title available?)
- scientific article; zbMATH DE number 3291134 (Why is no real title available?)
- Inductive inference of formal languages from positive data
- Language identification in the limit
- Learning in the presence of partial explanations
- LEARNING RECURSIVE LANGUAGES WITH BOUNDED MIND CHANGES
- Learning with the knowledge of an upper bound on program size
- Monotonic and dual monotonic language learning
- Prudence and other conditions on formal language learning
- Prudence in vacillatory language identification
- Research in the theory of inductive inference by GDR mathematicians - A survey
- Toward a mathematical theory of inductive inference
- Investigations on measure-one identification of classes of languages
- Characterizing language identification by standardizing operations
- Identifying terminal distinguishable languages
- Inductive inference and computable numberings
- Effectivity questions for Kleene's recursion theorem
- scientific article; zbMATH DE number 3859102 (Why is no real title available?)
- Learning in Friedberg Numberings
- The position of index sets of identifiable sets in the arithmetical hierarchy
- scientific article; zbMATH DE number 2077152 (Why is no real title available?)
- Inductive inference systems for learning classes of algorithmically generated sets and structures
- Synthesizing noise-tolerant language learners
- A learning-theoretic characterization of classes of recursive functions
- Learning in Friedberg numberings
This page was built for publication: Characterizing language identification in terms of computable numberings
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q676311)
