Loading...
Please wait, while we are loading the content...
Similar Documents
On the Learnability of Vector Spaces
| Content Provider | CiteSeerX |
|---|---|
| Author | Harizanov, Valentina S. Stephan, Frank |
| Abstract | The central topic of the paper is the learnability of the recursively enumerable subspaces of V1=V , where V1 is the standard recursive vector space over the rationals with countably in nite dimension, and V is a given recursively enumerable subspace of V1 . It is shown that certain types of vector spaces can be characterized in terms of learnability properties: V1=V is behaviourally correct learnable from text i V is nite dimensional, V1=V is behaviourally correct learnable from switching the type of information i V is nite dimensional, 0-thin, or 1-thin. On the other hand, learnability from informant does not correspond to similar algebraic properties of a given space. There are 0-thin spaces W 1 and W 2 such that W 1 is not explanatorily learnable from informant and the in nite product (W 1 ) is not behaviourally correct learnable, while W 2 and the in nite product (W 2 ) are both explanatorily learnable from informant. |
| File Format | |
| Access Restriction | Open |
| Subject Keyword | Vector Space Nite Product Enumerable Subspace Nite Dimension Certain Type Learnability Property Central Topic Standard Recursive Vector Space Similar Algebraic Property 0-thin Space |
| Content Type | Text |
