Uncountable Automatic Classes and Learning
No Thumbnail Available
Date
2009-02-02T08:30:27Z
Journal Title
Journal ISSN
Volume Title
Publisher
Abstract
In this paper we consider uncountable classes recognizable by omega-automata and investigate suitable learning paradigms for them.
In particular, the counterparts of explanatory, vacillatory and behaviourally correct learning are introduced for this setting. Here the learner reads in parallel the data of a text for a language L from the class plus an omega-index alpha and outputs a sequence of omega-automata such that all but finitely many of these omega-automata accept the index alpha if and only if alpha is an index for L.