Please use this identifier to cite or link to this item: https://doi.org/10.1016/j.ic.2016.09.001
Title: Enlarging learnable classes
Authors: Jain S. 
Kötzing T.
Stephan F. 
Keywords: Inductive inference
Learning in the limit
Non-union theorem
Total recursive functions
Issue Date: 2016
Publisher: Elsevier Inc.
Citation: Jain S., Kötzing T., Stephan F. (2016). Enlarging learnable classes. Information and Computation 251 : 194-207. ScholarBank@NUS Repository. https://doi.org/10.1016/j.ic.2016.09.001
Abstract: We study which classes of recursive functions satisfy that their union with any other explanatorily learnable class of recursive functions is again explanatorily learnable. We provide sufficient criteria for classes of recursive functions to satisfy this property and also investigate its effective variants. Furthermore, we study the question which learners can be effectively extended to learn a larger class of functions. We solve an open problem by showing that there is no effective procedure which does this task on all learners which do not learn a dense class of recursive functions. However, we show that there are two effective extension procedures such that each learner is extended by one of them. © 2016 Elsevier Inc.
Source Title: Information and Computation
URI: https://scholarbank.nus.edu.sg/handle/10635/177531
ISSN: 0890-5401
DOI: 10.1016/j.ic.2016.09.001
Appears in Collections:Staff Publications
Elements

Show full item record
Files in This Item:
File Description SizeFormatAccess SettingsVersion 
enlarginglearnableclass.pdf298.32 kBAdobe PDF

OPEN

Post-printView/Download

Google ScholarTM

Check

Altmetric


Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.