6533b82cfe1ef96bd128f4fc
RESEARCH PRODUCT
Learning with belief levels
Rūsiņš FreivaldsJānis BārzdiņšCarl H. Smithsubject
CompletenessAxiom systemsbusiness.industryComputer Networks and CommunicationsApplied Mathematics010102 general mathematicsInductive inference02 engineering and technologyInductive reasoning01 natural sciencesBelief levelsPredicate (grammar)EpistemologyTheoretical Computer ScienceTheoryofComputation_MATHEMATICALLOGICANDFORMALLANGUAGESComputational Theory and Mathematics020204 information systems0202 electrical engineering electronic engineering information engineeringLearningArtificial intelligence0101 mathematicsbusinessAction axiomAxiomMathematicsdescription
AbstractWe study learning of predicate logics formulas from “elementary facts,” i.e. from the values of the predicates in the given model. Several models of learning are considered, but most of our attention is paid to learning with belief levels. We propose an axiom system which describes what we consider to be a human scientist's natural behavior when trying to explore these elementary facts. It is proved that no such system can be complete. However we believe that our axiom system is “practically” complete. Theorems presented in the paper in some sense confirm our hypothesis.
| year | journal | country | edition | language |
|---|---|---|---|---|
| 2008-06-01 | Journal of Computer and System Sciences |