Abstract
There have been two principal approaches to the problem of concept learning. The first, empirical learning (also known as similarity-based learning), finds concept descriptions that best cover a set of training data without the use of an extensive theory of the domain. The candidate-elimination algorithm is one example of empirical learning. The second approach, analytical-learning (also known as explanation-based learning) (Mitchell et al., 1986; DeJong and Mooney, 1986), finds the weakest preconditions on a knowledge-based analysis of a single instance, forming a generalization that covers all instances that have the same analysis.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
Author information
Authors and Affiliations
Rights and permissions
Copyright information
© 1990 Kluwer Academic Publishers
About this chapter
Cite this chapter
Hirsh, H. (1990). Combining Empirical and Analytical Learning. In: Incremental Version-Space Merging: A General Framework for Concept Learning. The Kluwer International Series in Engineering and Computer Science, vol 104. Springer, Boston, MA. https://doi.org/10.1007/978-1-4613-1557-5_5
Download citation
DOI: https://doi.org/10.1007/978-1-4613-1557-5_5
Publisher Name: Springer, Boston, MA
Print ISBN: 978-1-4612-8834-3
Online ISBN: 978-1-4613-1557-5
eBook Packages: Springer Book Archive