Montagna, Franco; Simi, Giulia Paradigms in measure theoretic learning and in informant learning. (English) Zbl 0924.68172 Stud. Log. 62, No. 2, 243-268 (1999). Summary: 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 \(\delta\) canonical) are equivalent to the corresponding paradigms for identification on informants. Cited in 1 Document MSC: 68T05 Learning and adaptive systems in artificial intelligence 68Q45 Formal languages and automata 03D80 Applications of computability and recursion theory Keywords:classes of languages PDFBibTeX XMLCite \textit{F. Montagna} and \textit{G. Simi}, Stud. Log. 62, No. 2, 243--268 (1999; Zbl 0924.68172) Full Text: DOI