ISSN:
1572-8730
Keywords:
identification
;
learning
;
probability
;
informants
Source:
Springer Online Journal Archives 1860-2000
Topics:
Mathematics
,
Philosophy
Notes:
Abstract We investigate many paradigms of identifications for classes of languages (namely: consistent learning, EX learning, learning with finitely many errors, behaviorally correct learning, and behaviorally correct learning with finitely many errors) in a measure-theoretic context, and we relate such paradigms to their analogues in learning on informants. Roughly speaking, the results say that most paradigms in measure-theoretic learning wrt some classes of distributions (called δ canonical) are equivalent to the corresponding paradigms for identification on informants.
Type of Medium:
Electronic Resource
URL:
http://dx.doi.org/10.1023/A:1026455720278
Permalink