IBM/LNN
A `Neural = Symbolic` framework for sound and complete weighted real-value logic
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.
Stars
308
Forks
471
Language
Python
License
Apache-2.0
Category
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.
Related frameworks
pytorch/pytorch
Tensors and Dynamic neural networks in Python with strong GPU acceleration
keras-team/keras
Deep Learning for humans
Lightning-AI/torchmetrics
Machine learning metrics for distributed, scalable PyTorch applications.
Lightning-AI/pytorch-lightning
Pretrain, finetune ANY AI model of ANY size on 1 or 10,000+ GPUs with zero code changes.
lanpa/tensorboardX
tensorboard for pytorch (and chainer, mxnet, numpy, ...)