Logic Tensor Networks: Deep Learning and Logical Reasoning from Data and Knowledge

TL;DR

Logic Tensor Networks combine deep learning and logical reasoning by interpreting formulas with real-valued truth in a unified framework, enabling knowledge reasoning and data-driven learning.

Contribution

This work introduces Real Logic and demonstrates its implementation in Tensor Neural Networks for integrating reasoning with deep learning.

Findings

Successful implementation of Logic Tensor Networks using TensorFlow

Effective knowledge completion with the proposed framework

Unified approach to reasoning and learning from data

Abstract

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.