Abstract | ||
---|---|---|
Based on the observation that the category of concept spaces with the positive information topology is equivalent to the category
of countably based T
0 topological spaces, we investigate further connections between the learning in the limit model of inductive inference and
topology. In particular, we show that the “texts” or “positive presentations” of concepts in inductive inference can be viewed
as special cases of the “admissible representations” of computable analysis. We also show that several structural properties
of concept spaces have well known topological equivalents. In addition to topological methods, we use algebraic closure operators
to analyze the structure of concept spaces, and we show the connection between these two approaches. The goal of this paper
is not only to introduce new perspectives to learning theorists, but also to present the field of inductive inference in a
way more accessible to domain theorists and topologists.
|
Year | DOI | Venue |
---|---|---|
2008 | 10.1007/978-3-540-87987-9_31 | Algorithmic Learning Theory |
Keywords | Field | DocType |
topological properties,algebraic closure operator,admissible representation,t0topological space,computable analysis,concept spaces,domain theorist,concept space,topological equivalent,positive information topology,inductive inference,positive presentation,topological space,closure operator | Discrete mathematics,Topology,Topological space,Category of topological spaces,Computer science,Specialization (pre)order,Topological vector space,Compact-open topology,T1 space,Topological tensor product,Homeomorphism | Conference |
Volume | ISSN | Citations |
5254 | 0302-9743 | 7 |
PageRank | References | Authors |
0.59 | 16 | 2 |
Name | Order | Citations | PageRank |
---|---|---|---|
de brecht | 1 | 128 | 10.77 |
Akihiro Yamamoto | 2 | 135 | 26.84 |