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.

翻译：我们提出了一个称为TensorLog(TensorLog)的概率一阶逻辑,在这种逻辑逻辑中,将各种逻辑查询编成诸如Tensorflow(Tensorflow)或Theano(Theano)等神经网络基础设施的不同功能,从而将概率逻辑推理与深层次学习基础设施紧密结合:特别是,它使高性能深层次学习框架能够用于调整概率逻辑参数。实验结果表明,TensorLog(TensorLog)的尺度与涉及数十万个知识基三倍和数万个实例的问题有关。