arXiv (Cornell University) · 2017 · 14 citations · 21 references
ComputingComputer ScienceMathematicsLogicMachine LearningTheory Of ComputationFirst-order LogicPredicate LogicDeclarative SemanticsDefinabilityDefinability Theory
We consider a declarative framework for machine learning where concepts and hypotheses are defined by formulas of a logic over some structure. We show that within this framework, concepts defined by first-order formulas over a background structure of at most polylogarithmic degree can be learned in polylogarithmic time in the probably approximately correct learning sense.
21
Learnability and the Vapnik-Chervonenkis dimension
Anselm Blumer, Andrzej Ehrenfeucht, David Haussler et al. · Journal of the ACM · 1989 · 1.9K citations · Full text
Inductive Logic Programming: Theory and methods
Stephen Muggleton, Luc De Raedt · The Journal of Logic Programming · 1994 · 1.6K citations · Full text