Please use this identifier to cite or link to this item:
Title: Counting extensional differences in BC-learning
Authors: Jain, S. 
Stephan, F.
Terwijn, S.A.
Keywords: Behaviourally correct learning
Inductive inference
Models of grammar induction
Issue Date: 2004
Citation: Jain, S., Stephan, F., Terwijn, S.A. (2004). Counting extensional differences in BC-learning. Information and Computation 188 (1) : 127-142. ScholarBank@NUS Repository.
Abstract: Let BC be the model of behaviourally correct function learning as introduced by Bārzdins [Theory of Algorithms and Programs, vol. 1, Latvian State University, 1974, p. 82-88] and Case and Smith [Theoret. Comput. Sci. 25 (1983) 193-220]. We introduce a mind change hierarchy for BC, counting the number of extensional differences in the hypotheses of a learner. We compare the resulting models BC n to models from the literature and discuss confidence, team learning, and finitely defective hypotheses. Among other things, we prove that there is a trade-off between the number of semantic mind changes and the number of anomalies in the hypotheses. We also discuss consequences for language learning. In particular we show that, in contrast to the case of function learning, the family of classes that are confidently BC-learnable from text is not closed under finite unions. © 2003 Elsevier Inc. All rights reserved.
Source Title: Information and Computation
ISSN: 08905401
DOI: 10.1016/S0890-5401(03)00174-3
Appears in Collections:Staff Publications

Show full item record
Files in This Item:
There are no files associated with this item.


checked on Aug 5, 2020


checked on Aug 5, 2020

Page view(s)

checked on Aug 4, 2020

Google ScholarTM



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