Skip to yearly menu bar Skip to main content


Poster

DeepProbLog: Neural Probabilistic Logic Programming

Robin Manhaeve · Sebastijan Dumancic · Angelika Kimmig · Thomas Demeester · Luc De Raedt

Room 517 AB #118

Keywords: [ Deep Learning ] [ Probabilistic Methods ] [ Relational Learning ] [ Program Induction ]


Abstract:

We introduce DeepProbLog, a probabilistic logic programming language that incorporates deep learning by means of neural predicates. We show how existing inference and learning techniques can be adapted for the new language. Our experiments demonstrate that DeepProbLog supports (i) both symbolic and subsymbolic representations and inference, (ii) program induction, (iii) probabilistic (logic) programming, and (iv) (deep) learning from examples. To the best of our knowledge, this work is the first to propose a framework where general-purpose neural networks and expressive probabilistic-logical modeling and reasoning are integrated in a way that exploits the full expressiveness and strengths of both worlds and can be trained end-to-end based on examples.

Live content is unavailable. Log in and register to view live content