logictensornetworks/LTNtorch
PyTorch implementation of Logic Tensor Networks, a Neural-Symbolic framework.
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.
Stars
38
Forks
6
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/logictensornetworks/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, ...)