Article details

: Deep learning for probabilistic logic programming

: In Marco Rospocher, Luciano Serafini, and Sara Tonelli, editors, AI*IA 2018 Doctoral Consortium, Proceedings of the AI*IA Doctoral Consortium (DC), volume 2249 of CEUR Workshop Proceedings, pages 43--47, Aachen, Germany, 2018. © by the authors, Sun SITE Central Europe.


In this paper we present various approaches for speeding up learning. We first consider a restriction of PLP called Liftable PLP (LPLP) in which clauses in the program share the same predicate (the target). Then we extend this restriction in Hierarchical PLP (HPLP) where predicates and clauses are hierarchically organized and can be translated into Deep Neural Networks or Arithmetic Circuits.

Published at: 17th International Conference of the Italian Association for Artificial Intelligence (AI*IA 2018)

Download: [.pdf]