Knowledge-based learning: Integration of deductive and inductive learning for knowledge base completion

To learn effectively, a system needs to use all the knowledge that is available. Explanation-based learning and similarity-based learning operate over a domain theory and a set of examples, respectively, but neither approach makes extensive use of both forms of knowledge. Many problems in engineering and other areas can provide a learning system with an incomplete domain theory and a limited set of examples. Knowledge-based learning uses knowledge in both forms to learn knowledge missing from the domain theory.

Name thesis:degree_name

Ph.D.

Level thesis:degree_level

Dissertation

Discipline thesis:degree_discipline

Computer Science

Grantor

University of Illinois at Urbana-Champaign

Year dc:date

2011

Author dc:creator

• Whitehall, Bradley Lane

Contributors dc:contributor

• Lu, Stephen C-Y

• Artificial Intelligence
• Computer Science

Statement dc:rights

• Copyright 1990 Whitehall, Bradley Lane

Language dc:language

eng

Identifier

AAI9114461
(UMI)AAI9114461

OAI identifier oai:identifier

oai:www.ideals.illinois.edu:2142/22334