Deep Learning and Probabilistic Logic Programming

Visual of deep learning

DeepProbLog is an extension of ProbLog that integrates Probabilistic Logic Programming with deep learning by introducing the neural predicate. The neural predicate represents probabilistic facts whose probabilites are parameterized by neural networks. For more information, consult the papers listed below.

More Information:
  • Grand Challenge/Workpackage(s): GC1 - WP1, WP2
  • Responsible Research Lead: Luc De Raedt
  • Authors: Robin Manhaeve
  • Programming Language: Python
  • Link to the repository
  • Categories: Probabilistic programming, supervised learning, networks and graphs, relational databases, images
  • They can be found here