# Your search

MACHINE LEARNING

MODEL CHECKING AND STATE MACHINES

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

Resource type

Authors/contributors

- Serafini, Luciano (Author)
- Garcez, Artur d'Avila (Author)

Title

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.

Publication

arXiv:1606.04422 [cs]

Date

2016-07-07

Short Title

Logic Tensor Networks

Accessed

2019-11-24T16:33:44Z

Library Catalog

Extra

ZSCC: 0000057 arXiv: 1606.04422

Notes

Comment: 12 pages, 2 figs, 1 table, 27 references

Citation

Serafini, L., & Garcez, A. d’Avila. (2016). Logic Tensor Networks: Deep Learning and Logical Reasoning from Data and Knowledge.

*ArXiv:1606.04422 [Cs]*. Retrieved from http://arxiv.org/abs/1606.04422
MACHINE LEARNING

MODEL CHECKING AND STATE MACHINES

Attachment

Link to this record