logictensornetworks/LTNtorch

PyTorch implementation of Logic Tensor Networks, a Neural-Symbolic framework.

37
/ 100
Emerging

This framework helps data scientists and machine learning engineers build neural networks that incorporate logical rules and prior knowledge into their learning process. It takes your existing data and a set of logical statements (axioms) you want your model to follow, and outputs a neural network that has learned from both the data and these logical constraints. The end result is a model that adheres to specified logical relationships, making its decisions more interpretable and robust.

No commits in the last 6 months.

Use this if you need your machine learning models to respect predefined logical rules or knowledge, beyond just learning patterns from data.

Not ideal if your problem purely involves pattern recognition from data without any explicit logical constraints or prior knowledge to embed.

knowledge-representation neural-symbolic-AI explainable-AI constrained-learning semantic-reasoning
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 7 / 25
Maturity 16 / 25
Community 14 / 25

How are scores calculated?

Stars

38

Forks

6

Language

Python

License

MIT

Last pushed

Oct 02, 2024

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/logictensornetworks/LTNtorch"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.