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

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.

12 pages, 2 figs, 1 table, 27 references

References in corpus (2)

• From Machine Learning to Machine Reasoning
• Towards a Model Theory for Distributed Representations

Cited by in corpus (19)

• The Next Decade in AI: Four Steps Towards Robust Artificial Intelligence
• Logical Neural Networks
• TensorLog: Deep Learning Meets Probabilistic DBs
• Deep Learning for Ontology Reasoning
• Inductive Logic Programming via Differentiable Deep Neural Logic Networks
• Siamese recurrent networks learn first-order logic reasoning and exhibit zero-shot compositional generalization
• Knowledge Graph Embeddings and Explainable AI
• Learning Algorithms via Neural Logic Networks
• Modular Design Patterns for Hybrid Learning and Reasoning Systems: a taxonomy, patterns and use cases
• Logic Embeddings for Complex Query Answering
• Neural Network for Weighted Signal Temporal Logic
• Zero-Shot Learning with Knowledge Enhanced Visual Semantic Embeddings
• Neural Theorem Provers Do Not Learn Rules Without Exploration
• Ontology-based n-ball Concept Embeddings Informing Few-shot Image Classification
• An Insect-Inspired Randomly, Weighted Neural Network with Random Fourier Features For Neuro-Symbolic Relational Learning
• Randomly Weighted, Untrained Neural Tensor Networks Achieve Greater Relational Expressiveness
• Approximate Knowledge Graph Query Answering: From Ranking to Binary Classification
• Understanding in Artificial Intelligence
• Fit to Measure: Reasoning about Sizes for Robust Object Recognition