DeepProbLog: Neural Probabilistic Logic Programming

2018/05/28 by Robin Manhaeve, Manhaeve, Robin, Sebastijan Dumančić +7 · 3 citations
Computer Science · #Artificial Intelligence (cs.AI) #FOS: Computer and information sciences #Logic, Reasoning, and Knowledge #Natural Language Processing Techniques #Topic Modeling

paper · doi:10.48550/arxiv.1805.10872

openalex publication_date 2018/05/28 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/29

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 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.

Citations

• Gradient-based learning applied to document recognition

Cited by

• pix2rule: End-to-end Neuro-symbolic Rule Learning
• RuDaS: Synthetic Datasets for Rule Learning and Evaluation Tools
• On the Relevance of Logic for Artificial Intelligence, and the Promise of Neurosymbolic Learning

Related

• Neural Probabilistic Logic Programming in DeepProbLog
• DeepStochLog: Neural Stochastic Logic Programming
• Neural Probabilistic Logic Programming in Discrete-Continuous Domains
• TensorLog: Deep Learning Meets Probabilistic DBs
• DeepPSL: End-to-end perception and reasoning