Title
Learning families of closed sets in matroids
Abstract
In this paper it is studied for which oracles A and which types of A-r.e. matroids the class of all A-r.e. closed sets in the matroid is learnable by an unrelativised learner. The learning criteria considered comprise in particular criteria more general than behaviourally correct learning, namely behaviourally correct learning from recursive texts, partial learning and reliably partial learning. For various natural classes of matroids and learning criteria, characterisations of learnability are obtained.
Year
DOI
Venue
2012
10.1007/978-3-642-27654-5_10
Computation, Physics and Beyond
Keywords
Field
DocType
partial learning,recursive text,closed set,particular criterion,behaviourally correct learning,various natural class,unrelativised learner
Matroid,Inductive reasoning,Discrete mathematics,Closed set,Turing degree,Recursive functions,Learnability,Recursion,Mathematics
Conference
Citations 
PageRank 
References 
3
0.42
18
Authors
4
Name
Order
Citations
PageRank
Ziyuan Gao1196.94
Frank Stephan221539.36
Guohua Wu342.50
Akihiro Yamamoto413526.84