Logic Tensor Networks: Deep Learning and Logical Reasoning from Data and Knowledge
This work addresses the challenge of unifying symbolic reasoning and statistical learning for AI researchers, though it appears incremental as it builds on existing tensor network and logic formalisms.
The authors tackled the problem of integrating logical reasoning with deep learning by proposing Logic Tensor Networks, a framework that combines deductive reasoning on knowledge bases with data-driven relational machine learning, and demonstrated its application on a knowledge completion task.
We propose Logic Tensor Networks: a uniform framework for integrating automatic learning and reasoning. A logic formalism called Real Logic is defined on a first-order language whereby formulas have truth-value in the interval [0,1] and semantics defined concretely on the domain of real numbers. Logical constants are interpreted as feature vectors of real numbers. Real Logic promotes a well-founded integration of deductive reasoning on a knowledge-base and efficient data-driven relational machine learning. We show how Real Logic can be implemented in deep Tensor Neural Networks with the use of Google's tensorflow primitives. The paper concludes with experiments applying Logic Tensor Networks on a simple but representative example of knowledge completion.