Loading...
Please wait, while we are loading the content...
Similar Documents
Learning branches and learning to win closed games (extended abstract) (1996).
| Content Provider | CiteSeerX |
|---|---|
| Author | Kummer, Martin Ott, Matthias |
| Abstract | ) Martin Kummer and Matthias Ott Institut fur Logik, Komplexitat und Deduktionssysteme Universitat Karlsruhe, D-76128 Karlsruhe, Germany Email: fkummer; m ottg@ira.uka.de Abstract We introduce two new notions of inductive inference: learning infinite recursive branches of recursive trees and learning winning strategies for closed recursive games. Branch learning can be seen as a natural generalization of learning functions, and learning winning strategies is a new approach to constructively find winning strategies for a special kind of Gale-Stewart games. These two independently motivated concepts turn out to be equivalent. In branch learning there appear new phenomena compared to function learning: e.g. we can show that learning and uniform computation are incomparable. In the setting of learning functions uniform computation is trivial. Another example is that there are two distinct natural definitions for BC-style branch learning which yield different classes. By studying diffe... |
| File Format | |
| Publisher Date | 1996-01-01 |
| Access Restriction | Open |
| Subject Keyword | Extended Abstract Deduktionssysteme Universitat Karlsruhe Natural Generalization Uniform Computation Inductive Inference Different Class Distinct Natural Definition Recursive Tree D-76128 Karlsruhe Gale-stewart Game New Approach Learning Infinite Recursive Branch Function Uniform Computation Matthias Ott Institut Fur Logik Closed Recursive Game Special Kind New Notion Bc-style Branch Germany Email New Phenomenon |
| Content Type | Text |
