Some Results on Learning
Abstract
This paper presents some formal results on learning. In particular, it concerns algorithms that learn sets and functions from examples. We seek conditions necessary and sufficient for learning over a range of probabilistic models for such algorithms. This paper concerns algorithms that learn sets and functions from examples for them. The motivation behind the study is a need to better understand the class of problems known as 'concept learning problems' in the Artificial Intelligence literature.
Document Details
- Document Type
- Technical Report
- Publication Date
- Feb 01, 1989
- Accession Number
- ADA210591
Entities
People
- B. K. Natarajan
Organizations
- Carnegie Mellon University