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 both symbolic and subsymbolic representations and inference, 1) program induction, 2) probabilistic (logic) programming, and 3) (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.
@article{arxiv.1805.10872,
title = {DeepProbLog: Neural Probabilistic Logic Programming},
author = {Robin Manhaeve and Sebastijan Dumančić and Angelika Kimmig and Thomas Demeester and Luc De Raedt},
journal= {arXiv preprint arXiv:1805.10872},
year = {2018}
}