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 (45)

• The Next Decade in AI: Four Steps Towards Robust Artificial Intelligence
• Incorporating Domain Knowledge into Deep Neural Networks
• A Review of Some Techniques for Inclusion of Domain-Knowledge into Deep Neural Networks
• Graph Neural Networks Meet Neural-Symbolic Computing: A Survey and Perspective
• End-to-End Differentiable Proving
• Logical Neural Networks
• Is Neuro-Symbolic AI Meeting its Promise in Natural Language Processing? A Structured Review
• Deep Learning with Logical Constraints
• TensorLog: Deep Learning Meets Probabilistic DBs
• Deep Learning for Ontology Reasoning
• Inductive Logic Programming via Differentiable Deep Neural Logic Networks
• Beyond Graph Neural Networks with Lifted Relational Neural Networks
• On a Convex Logic Fragment for Learning and Reasoning
• Logical Rule Induction and Theory Learning Using Neural Theorem Proving
• Siamese recurrent networks learn first-order logic reasoning and exhibit zero-shot compositional generalization
• T-Norms Driven Loss Functions for Machine Learning
• Modular Design Patterns for Hybrid Learning and Reasoning Systems: a taxonomy, patterns and use cases
• Knowledge Graph Embeddings and Explainable AI
• Learning Algorithms via Neural Logic Networks
• Reasoning over RDF Knowledge Bases using Deep Learning
• DeepLogic: Towards End-to-End Differentiable Logical Reasoning
• Neural Markov Logic Networks
• Logic Embeddings for Complex Query Answering
• Learning of Human-like Algebraic Reasoning Using Deep Feedforward Neural Networks
• Neural Network for Weighted Signal Temporal Logic
• Deep Adaptive Semantic Logic (DASL): Compiling Declarative Knowledge into Deep Neural Networks
• Neural Theorem Provers Do Not Learn Rules Without Exploration
• Zero-Shot Learning with Knowledge Enhanced Visual Semantic Embeddings
• A Survey on Neural-symbolic Learning Systems
• Ontology-based n-ball Concept Embeddings Informing Few-shot Image Classification
• Trusted Neural Networks for Safety-Constrained Autonomous Control
• NSL: Hybrid Interpretable Learning From Noisy Raw Data
• A Probabilistic Model for Discriminative and Neuro-Symbolic Semi-Supervised Learning
• SLDR-DL: A Framework for SLD-Resolution with Deep Learning
• Learning Algebraic Representation for Systematic Generalization in Abstract Reasoning
• Neural Belief Reasoner
• An Insect-Inspired Randomly, Weighted Neural Network with Random Fourier Features For Neuro-Symbolic Relational Learning
• Knowledge-driven Active Learning
• Neural Networks Enhancement with Logical Knowledge
• Learning Invariants through Soft Unification
• Fit to Measure: Reasoning about Sizes for Robust Object Recognition
• Understanding in Artificial Intelligence
• Approximate Knowledge Graph Query Answering: From Ranking to Binary Classification
• Randomly Weighted, Untrained Neural Tensor Networks Achieve Greater Relational Expressiveness
• Neuron Coverage-Guided Domain Generalization