Abstract
Presented is a surprising characterization of hypersimple sets in algorithmic learning theory. It is used herein to obtain an elegant, tight separation result for learnability criteria. It is argued that such separation results may yield insight for eventual characterizations.
| Original language | English (US) |
|---|---|
| Pages (from-to) | 26-32 |
| Number of pages | 7 |
| Journal | Journal of Computer and System Sciences |
| Volume | 53 |
| Issue number | 1 |
| DOIs | |
| State | Published - Aug 1996 |
| Externally published | Yes |
All Science Journal Classification (ASJC) codes
- Theoretical Computer Science
- General Computer Science
- Computer Networks and Communications
- Computational Theory and Mathematics
- Applied Mathematics
Fingerprint
Dive into the research topics of 'Learnability: Admissible, co-finite, and hypersimple languages'. Together they form a unique fingerprint.Cite this
- APA
- Author
- BIBTEX
- Harvard
- Standard
- RIS
- Vancouver