GustikS/NeuraLogic
Deep relational learning through differentiable logic programming.
This is a backend framework for researchers and practitioners working with complex, interconnected data structures. It takes inputs like knowledge graphs, relational databases, or molecular structures, along with a set of logical rules, to produce classifications or predictions. It's designed for anyone needing to build deep learning models that can reason about relationships and infer new knowledge from structured data.
113 stars. No commits in the last 6 months.
Use this if you need to build deep learning models that incorporate prior knowledge or rules, especially when working with irregularly structured or relational data like graphs, hypergraphs, or ontologies.
Not ideal if your primary focus is classic deep learning on large, homogeneous datasets, such as image or text processing with standard convolutional or recurrent neural networks.
Stars
113
Forks
15
Language
Java
License
MIT
Category
Last pushed
Aug 09, 2025
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/GustikS/NeuraLogic"
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, ...)