IBM/LNN

A `Neural = Symbolic` framework for sound and complete weighted real-value logic

61
/ 100
Established

This framework helps AI researchers and machine learning practitioners build models that combine the strengths of neural networks with logical reasoning. You input existing knowledge, data, and problem rules, and it outputs models that can learn, reason, and provide interpretable results, even with incomplete or inconsistent information. It's designed for those who need AI systems that not only learn from data but also explain their decisions based on logical principles.

308 stars.

Use this if you need to create AI models that can integrate explicit rules and knowledge with machine learning capabilities, and require transparent, logically sound reasoning alongside data-driven insights.

Not ideal if you are looking for a straightforward, black-box predictive model without the need for logical interpretability or the integration of symbolic knowledge.

AI-research explainable-AI knowledge-representation machine-learning-engineering symbolic-reasoning
No Package No Dependents
Maintenance 10 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 25 / 25

How are scores calculated?

Stars

308

Forks

471

Language

Python

License

Apache-2.0

Last pushed

Mar 11, 2026

Commits (30d)

0

Get this data via API

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

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