tommasocarraro/LTNtorch
PyTorch implementation of Logic Tensor Networks, a Neural-Symbolic framework.
This project helps machine learning practitioners build models that incorporate existing domain knowledge and logical rules directly into their learning process. It takes your datasets and a set of logical statements (axioms) about your data, then trains neural networks to maximally satisfy these logical rules. The output is a more robust neural network model that adheres to specified logical constraints, useful for tasks like classification, regression, or clustering.
148 stars. No commits in the last 6 months.
Use this if you need to train neural networks where adhering to specific logical rules or domain knowledge is crucial for the model's reliability and performance.
Not ideal if your problem purely relies on data-driven patterns without any explicit logical constraints or prior knowledge to incorporate.
Stars
148
Forks
27
Language
Python
License
MIT
Category
Last pushed
Oct 02, 2024
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/tommasocarraro/LTNtorch"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
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, ...)