Prescribed Learning of Indexed Families
No Thumbnail Available
Date
2007-09-21T01:27:00Z
Authors
Journal Title
Journal ISSN
Volume Title
Publisher
Abstract
This work extends studies of Angluin, Lange and Zeugmann on how learnability of a language class depends on the hypotheses space used by the learner.
While previous studies mainly focused on the case where the learner chooses a particular hypotheses space, the goal of this work is to investigate the case where the learner has to cope with all possible hypotheses spaces.
In that sense, the present work combines the approach of Angluin, Lange and Zeugmann with the question of how a learner can be synthesized.
The investigation for the case of uniformly recursively enumerable classes has been presented by Jain, Stephan and Ye at the conference Algorithmic Learning Theory 2007. This paper investigates the case for indexed families and gives a special attention to the notions of conservative and non U-shaped learning.