Abstract

The lifted dynamic junction tree algorithm (LDJT) efficiently answers exact filtering and prediction queries for probabilistic relational temporal models by building and then reusing a first-order cluster representation of a knowledge base for multiple queries and time steps. We extend the underling model of LDJT to provide means to calculate a lifted temporal solution to the maximum expected utility problem. © CEUR-WS. All rights reserved.
OriginalspracheEnglisch
Titel1st Joint Workshop on AI in Health
Seitenumfang4
Band2142
Herausgeber (Verlag)CEUR-WS.org
Erscheinungsdatum01.07.2018
Seiten93-96
PublikationsstatusVeröffentlicht - 01.07.2018
Veranstaltung1st Joint Workshop on AI in Health - Stockholm, Schweden
Dauer: 13.07.201814.07.2018
Konferenznummer: 138105

DFG-Fachsystematik

  • 409-01 Theoretische Informatik

Zitieren