Definition
Inverse entailment is a generality relation in inductive logic programming. More specifically, when learning from entailment using a background theory B, a hypothesis H covers an example e, relative to the background theory B if and only if B ∧ H⊧e, that is, the background theory B and the hypothesis H together entail the example (see entailment). For instance, consider the background theory B:
bird :- blackbird.
bird :- ostrich.
and the hypothesis H:
flies :- bird.
Together B ∧ H entail the example e :
flies :- blackbird, normal.
This can be decided through deductive inference. Now when learning from entailment in inductive logic programming, one starts from the example e and the background theory B, and the aim is to induce a rule H that together with B entails the example. Inverting entailment is based on the observation that B ∧ H⊧e is logically equivalent to B ∧ ¬e⊧ ¬H, which in turn can be used to compute a hypothesis Hthat will cover the example relative to the...
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2011 Springer Science+Business Media, LLC
About this entry
Cite this entry
(2011). Inverse Entailment. In: Sammut, C., Webb, G.I. (eds) Encyclopedia of Machine Learning. Springer, Boston, MA. https://doi.org/10.1007/978-0-387-30164-8_415
Download citation
DOI: https://doi.org/10.1007/978-0-387-30164-8_415
Publisher Name: Springer, Boston, MA
Print ISBN: 978-0-387-30768-8
Online ISBN: 978-0-387-30164-8
eBook Packages: Computer ScienceReference Module Computer Science and Engineering