Expressive power of safe first-order logical decision trees

Authors:
Joris J. M. Gillis;Jan Van den Bussche
Affiliations:
Hasselt University, Belgium,Transnational University of Limburg, Belgium;Hasselt University, Belgium,Transnational University of Limburg, Belgium
Venue:
ILP'11 Proceedings of the 21st international conference on Inductive Logic Programming
Year:
2011

Citing 6
Cited 0

Principles of database and knowledge-base systems, Vol. I

Principles of database and knowledge-base systems, Vol. I
A universal inductive inference machine

Journal of Symbolic Logic
A General Theory of Deduction, Induction, and Learning

DS '01 Proceedings of the 4th International Conference on Discovery Science
Logical and Relational Learning: From ILP to MRDM (Cognitive Technologies)

Logical and Relational Learning: From ILP to MRDM (Cognitive Technologies)
Improving the efficiency of inductive logic programming through the use of query packs

Journal of Artificial Intelligence Research
Top-down induction of first-order logical decision trees

Artificial Intelligence

Quantified Score

Hi-index	0.00

Visualization

Abstract

This paper characterizes the expressive power of a subclass of first-order logical decision trees (FOLDTs) as a fragment of first-order logic. Specifically, using safe FOLDTs one can express precisely the boolean combinations of safe existential sentences.