Name
Abstract | ||
|---|---|---|
A new view of learning is presented. The basis of this view is a natural notion of reduction. We prove completeness and relative difficulty results. An infinite hierarchy of intrinsically more and more difficult to learn concepts is presented. Our results indicate that the complexity notion captured by our new notion of reduction differs dramatically from the traditional studies of the complexity of the algorithms performing learning tasks. |
Year | DOI | Venue |
|---|---|---|
1995 | 10.1006/inco.1995.1158 | Information & Computation |
Keywords | DocType | Volume |
intrinsic complexity | Conference | 123 |
Issue | ISSN | ISBN |
1 | Information and Computation | 3-540-59119-2 |
Citations | PageRank | References |
33 | 1.30 | 16 |
Authors | ||
3 | ||
Name | Order | Citations | PageRank |
|---|---|---|---|
| Rūsiņš Freivalds | 1 | 249 | 20.26 |
| Efim Kinber | 2 | 421 | 44.95 |
| Carl H. Smith | 3 | 33 | 1.30 |