Abstract
The model of learning used here is acquiring and developing a hierarchical structure from a set of instances. The hierarchy that is realized is a lattice. The learning sequence is:
-
1.
From a set of learning instances construct descriptions of the objects to be learned.
-
2.
Abstracting from the learned objects, generate new objects that subsume the given objects.
-
3.
Build an inheritance lattice that includes all of the objects — both the learning instances and the objects abstracted from them.
-
4.
Learn new objects and refine the inheritance lattice to include these objects.
Dr. Dale Parson of Lucent Technologies recommended that we include some discussion — and examples — of machine learning. He has a draft of a more ambitious learning program. He can be reached at dale@aloft.att.com.
This is a preview of subscription content, log in via an institution to check access.
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
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 1996 AT&T Bell Laboratories
About this chapter
Cite this chapter
Kowalski, T.J., Levy, L.S. (1996). Machine Learning. In: Kowalski, T.J., Levy, L.S. (eds) Rule-Based Programming. The Kluwer International Series in Engineering and Computer Science, vol 369. Springer, Boston, MA. https://doi.org/10.1007/978-1-4613-1435-6_7
Download citation
DOI: https://doi.org/10.1007/978-1-4613-1435-6_7
Publisher Name: Springer, Boston, MA
Print ISBN: 978-1-4612-8624-0
Online ISBN: 978-1-4613-1435-6
eBook Packages: Springer Book Archive