A new algorithm to automate inductive learning of default theories

In inductive learning of a broad concept, an algorithm should be able to distinguish concept examples from exceptions and noisy data. An approach through recursively finding patterns in exceptions turns out to correspond to the problem of learning default theories. Default logic is what humans emplo...

Celý popis

Uloženo v:
Podrobná bibliografie
Vydáno v:Theory and practice of logic programming Ročník 17; číslo 5-6; s. 1010 - 1026
Hlavní autoři: SHAKERIN, FARHAD, SALAZAR, ELMER, GUPTA, GOPAL
Médium: Journal Article
Jazyk:angličtina
Vydáno: Cambridge, UK Cambridge University Press 01.09.2017
Témata:
Algorithms
Logic programming
Logic programs
Machine learning
Regular Papers
non-monotonic logic programming
machine learning
default reasoning
common-sense reasoning
inductive logic programming
ISSN:1471-0684, 1475-3081
On-line přístup:Získat plný text
Tagy: Přidat tag
Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!
Popis
Shrnutí:In inductive learning of a broad concept, an algorithm should be able to distinguish concept examples from exceptions and noisy data. An approach through recursively finding patterns in exceptions turns out to correspond to the problem of learning default theories. Default logic is what humans employ in common-sense reasoning. Therefore, learned default theories are better understood by humans. In this paper, we present new algorithms to learn default theories in the form of non-monotonic logic programs. Experiments reported in this paper show that our algorithms are a significant improvement over traditional approaches based on inductive logic programming. Under consideration for acceptance in TPLP.
Bibliografie:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
ISSN:1471-0684
1475-3081
DOI:10.1017/S1471068417000333