DeepProbLog: Neural Probabilistic Logic Programming
This work addresses the challenge of combining neural networks with probabilistic-logical reasoning for researchers in AI and machine learning, offering a novel framework that integrates both approaches.
The authors tackled the integration of deep learning with probabilistic logic programming by introducing DeepProbLog, a language that incorporates neural predicates, enabling end-to-end training and supporting symbolic and subsymbolic representations, with experiments demonstrating capabilities in program induction, probabilistic programming, and learning from examples.
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.