# DeepProbLog: Neural Probabilistic Logic Programming

arXiv: https://arxiv.org/abs/1805.10872 · HTML: https://mlsanity.com/paper/1805.10872/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 28 May 2018.

## Built on by (most cited first, 6 of 6)

- [Automated Theorem Provers Help Improve Large Language Model Reasoning](https://mlsanity.com/paper/2408.03492/) (2024)
- [Attention as Binding: A Vector-Symbolic Perspective on Transformer Reasoning](https://mlsanity.com/paper/2512.14709/) (2025)
- [Approaches to human activity recognition via passive radar](https://mlsanity.com/paper/2410.24166/) (2024)
- [Weakly Supervised Concept Learning for Object-centric Visual Reasoning](https://mlsanity.com/paper/2605.08201/) (2026)
- [Weakly supervised concept Bottleneck Learning for Robust Two stage Object centric visual reasoning](https://mlsanity.com/paper/2608.22584/) (2026)
- [Uncertainty in Representation Learning on Knowledge Graphs](https://mlsanity.com/paper/2610.06974/) (2026)

## Abstract (arXiv)

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.