We introduce DeepProbLog, a neural probabilistic logic programming language that incorporates deep learning by means of neural predicates. We show how existing inference and learning techniques of the underlying probabilistic logic programming language ProbLog can be adapted for the new language. We theoretically and experimentally demonstrate that DeepProbLog supports (i) both symbolic and subsymbolic representations and inference, (ii) program induction, (iii) probabilistic (logic) programming, and (iv) (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.

我们介绍DeepProbLog，这是一种神经概率逻辑编程语言，它通过神经谓词结合了深度学习。我们展示了基础概率逻辑编程语言ProbLog的现有推理和学习技术如何能够适应新语言。我们在理论上和实验上证明了DeepProbLog支持（i）符号和子符号表示与推论，（ii）程序归纳，（iii）概率（逻辑）编程以及（iv）（深度）从示例中学习。就我们所知，这项工作是第一个提出一个框架的框架，该框架将通用神经网络与表达概率逻辑建模和推理进行整合，从而可以充分利用两个世界的全部表达能力和优势，并可以对其进行培训。 -以示例为基础。