Abductive explanation-based learning: A solution to the multiple inconsistent explanation problem (Q1189662): Difference between revisions
From MaRDI portal
Removed claim: reviewed by (P1447): Item:Q469832 |
Set profile property. |
||
(One intermediate revision by one other user not shown) | |||
Property / reviewed by | |||
Property / reviewed by: Luminita State / rank | |||
Normal rank | |||
Property / MaRDI profile type | |||
Property / MaRDI profile type: MaRDI publication profile / rank | |||
Normal rank |
Latest revision as of 03:28, 5 March 2024
scientific article
Language | Label | Description | Also known as |
---|---|---|---|
English | Abductive explanation-based learning: A solution to the multiple inconsistent explanation problem |
scientific article |
Statements
Abductive explanation-based learning: A solution to the multiple inconsistent explanation problem (English)
0 references
27 September 1992
0 references
Frequently, as an effect of the incompleteness and incorrectness of the available information, domain theories produce multiple explanations for training instances, not all of them are correct. The issue proposes the abductive explanation-based learning (A-EBL) as an attempt to solve the multiple inconsistent explanation problem mainly based on using negative examples and set covering techniques. The EBL/TS and the abductive-EBL algorithms are presented in the second section. A formal treatment of A-EBL and EBL/TS, expressed in terms of theoretical results concerning competence and convergence properties, is developed in the next section. Some experimental results on A-EBL are also reported. It is proved that the A-EBL has convergence properties only logarithmically worse than EBL/TS and that A-EBL is computationally efficient when the domain theory is tractable.
0 references
theory specialization
0 references
theory revision
0 references
probably approximately correct learning
0 references
explanation-based learning
0 references