✦ LIBER ✦

Inductive Inference with Additional Information

✍ Scribed by Mark Fulk

Publisher: Elsevier Science
Year: 2002
Tongue: English
Weight: 113 KB
Volume: 64
Category: Article
ISSN: 0022-0000
DOI: 10.1006/jcss.2000.1702

No coin nor oath required. For personal study only.

✦ Synopsis

We consider the problem of inductively inferring a grammar for a language, given (positive) examples of the language and putative (possibly faulty) grammars for the complement of the language. The criterion of success is identification in the limit, defined by E. M. Gold (1967, Inform. and Control 10, 447 474). Additional information is useful insofar as it allows the identification of language classes that would not be identified with positive examples alone. An infinite sequence of grammars past some finite position are correct for the complement of the input language, is not as useful a form of additional information as a single correct grammar for the complement. Grammars that are almost correct for the complement (that is, that make finitely many errors) are not as useful as correct grammars, and the usefulness of a grammar decreases with increasing numbers of errors.

📜 SIMILAR VOLUMES

On a method of inductive inference with

On a method of inductive inference with decision-tree pruning

✍ A. M. Gupal; A. A. Ponomarev; A. M. Tsvetkov 📂 Article 📅 1994 🏛 Springer US 🌐 English ⚖ 317 KB

Minimum-contrast estimation with additio

Minimum-contrast estimation with additional information

✍ M. V. Gal'chenko; V. A. Gurevich 📂 Article 📅 1991 🏛 Springer US 🌐 English ⚖ 332 KB

Sensitivity of information conversion wi

Sensitivity of information conversion with inductive-capacitive transducers

✍ S. I. Pyatin 📂 Article 📅 1977 🏛 Springer US 🌐 English ⚖ 184 KB

Additional utility of insiders with impe

Additional utility of insiders with imperfect dynamical information

✍ JoséM. Corcuera; Peter Imkeller; Arturo Kohatsu-Higa; David Nualart 📂 Article 📅 2004 🏛 Springer-Verlag 🌐 English ⚖ 208 KB

Improved Monte Carlo inference for model

Improved Monte Carlo inference for models with additive error

✍ Martin Hazelton 📂 Article 📅 1995 🏛 Springer US 🌐 English ⚖ 814 KB

Some statistical models defined in terms of a generating stochastic mechanism have intractable distribution theory, which renders parameter estimation difficult. However, a Monte Carlo estimate of the log-likelihood surface for such a model can be obtained via computation of nonparametric density es

Updating non-additive measures with fuzz

Updating non-additive measures with fuzzy information

✍ Virginia R. Young; Shaun S. Wang 📂 Article 📅 1998 🏛 Elsevier Science 🌐 English ⚖ 589 KB

We present several rules for updating non-additive set functions, defined and conditioned on fuzzy sets. Among these formulas are the Dempster-Shafer rule for belief functions and the Bayes' conditioning rule. We develop the update formulas in the framework of non-additive measure and integration th