DMCA
On the Synthesis of Strategies Identifying Recursive Functions (2001)
Cached
Download Links
- [www2.cs.uregina.ca]
- [www2.cs.uregina.ca]
- DBLP
Other Repositories/Bibliography
| Venue: | Proceedings of the 14th Annual Conference on Computational Learning Theory, Lecture Notes in Artificial Intelligence 2111 |
| Citations: | 3 - 3 self |
BibTeX
@INPROCEEDINGS{Zilles01onthe,
author = {Sandra Zilles and Fachbereich Informatik and Universität Kaiserslautern},
title = {On the Synthesis of Strategies Identifying Recursive Functions},
booktitle = {Proceedings of the 14th Annual Conference on Computational Learning Theory, Lecture Notes in Artificial Intelligence 2111},
year = {2001},
pages = {160--176},
publisher = {Springer-Verlag}
}
Share
 |
 |
 |
 |
||
OpenURL
Abstract
Abstract. A classical learning problem in Inductive Inference consists of identifying each function of a given class of recursive functions from a finite number of its output values. Uniform learning is concerned with the design of single programs solving infinitely many classical learning problems. For that purpose the program reads a description of an identification problem and is supposed to construct a technique for solving the particular problem. As can be proved, uniform solvability of collections of solvable identification problems is rather influenced by the description of the problems than by the particular problems themselves. When prescribing a specific inference criterion (for example learning in the limit), a clever choice of descriptions allows uniform solvability of all solvable problems, whereas even the most simple classes of recursive functions are not uniformly learnable without restricting the set of possible descriptions. Furthermore the influence of the hypothesis spaces on uniform learnability is analysed. 1
Keyphrases
strategy identifying recursive function particular problem recursive function example learning single program simple class finite number uniform learnability classical learning problem possible description clever choice solvable identification problem solvable problem uniform learning inductive inference output value uniform solvability description allows uniform solvability hypothesis space many classical learning problem specific inference criterion identification problem
