Neural probabilistic logic programming in DeepProbLog

DOI10.1016/j.artint.2021.103504OpenAlexW3154009503MaRDI QIDQ2238688

Angelika Kimmig, Robin Manhaeve, Sebastijan Dumančić, Luc De Raedt, Thomas Demeester

Publication date: 2 November 2021

Published in: Artificial Intelligence (Search for Journal in Brave)

Full work available at URL: https://arxiv.org/abs/1907.08194

zbMATH Keywords

neural networksprobabilitylogicprobabilistic logic programmingneuro-symbolic integrationlearning and reasoning

Mathematics Subject Classification ID

Artificial intelligence (68Txx)

Related Items (9)

Efficient Knowledge Compilation Beyond Weighted Model Counting ⋮ Logic tensor networks ⋮ FFNSL: Feed-forward neural-symbolic learner ⋮ \(\alpha\)ILP: thinking visual scenes as differentiable logic programs ⋮ Online event recognition over noisy data streams ⋮ Unnamed Item ⋮ Unnamed Item ⋮ Weighted defeasible knowledge bases and a multipreference semantics for a deep neural network model ⋮ Injecting domain knowledge in neural networks: a controlled experiment on a constrained problem

Uses Software

• ProbLog
• PyTorch
• Adam
• TensorLog
• CLUTRR
• DeepProbLog
• RelNN
• NLProlog

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Semantic-based regularization for learning and inference
• Probabilistic (logic) programming concepts
• Perspectives of neural-symbolic integration.
• Algebraic model counting
• Markov logic networks
• Statistical Relational Artificial Intelligence: Logic, Probability, and Computation
• Markov Logic: An Interface Layer for Artificial Intelligence
• The well-founded semantics for general logic programs
• Inference and learning in probabilistic logic programs using weighted Boolean formulas
• Learning Explanatory Rules from Noisy Data
• On the Efficient Execution of ProbLog Programs

This page was built for publication: Neural probabilistic logic programming in DeepProbLog