Learning at the knowledge level

Technical Report

Public Deposited

Citeable URL: https://ir.library.oregonstate.edu/concern/technical_reports/f1881v16p

Descriptions

Attribute Name	Values
Creator	Dietterich, Thomas G.
Abstract	When Newell introduced the concept of the knowledge level as a useful level of description for computer systems, he focused on the representation of knowledge. This paper applies the knowledge level notion to the problem of knowledge acquisition. Two interesting issues arise. First, some existing machine learning programs appear to be completely static when viewed at the knowledge level. These programs improve their performance without changing their "knowledge." Second, the behavior of some other machine learning programs cannot be predicted or described at the knowledge level. These programs take unjustified inductive leaps. The first programs are called symbol level learning (SLL) programs; the second, .non-deductive knowledge level learning (NKLL) programs. The paper analyzes both of these classes of learning programs and speculates on the possibility of developing coherent theories of each. A theory of symbol level learning is sketched, and some reasons are presented for believing that a theory of NKLL will be difficult to obtain.
Resource Type	Technical Report
Date Issued	1986
Academic Affiliation	Computer Science
Series	Technical report (Oregon State University. Department of Computer Science)
Rights Statement	In Copyright
Publisher	Oregon State University. Department of Computer Science
Language	English [eng]

Thumbnail	Title	Date Uploaded	Visibility	Actions
	Dietterich_Thomas_G_86_30_01.pdf	2023-01-26	Public	Download