We present an implementation of a probabilistic first-order logic called TensorLog, in which classes of logical queries are compiled into differentiable functions in a neural-network infrastructure such as Tensorflow or Theano. This leads to a close integration of probabilistic logical reasoning with deep-learning infrastructure: in particular, it enables high-performance deep learning frameworks to be used for tuning the parameters of a probabilistic logic. Experimental results show that TensorLog scales to problems involving hundreds of thousands of knowledge-base triples and tens of thousands of examples.
@article{arxiv.1707.05390,
title = {TensorLog: Deep Learning Meets Probabilistic DBs},
author = {William W. Cohen and Fan Yang and Kathryn Rivard Mazaitis},
journal= {arXiv preprint arXiv:1707.05390},
year = {2017}
}