attractivechaos/kann
A lightweight C library for artificial neural networks
This is a lightweight C library for building and training neural networks. It allows you to define complex network structures, like recurrent neural networks or those with shared weights, and then train them with your data. The library outputs a trained model that can be deployed to make predictions. This tool is for C/C++ developers who need to integrate neural network models directly into their applications or embedded systems without heavy dependencies.
746 stars. No commits in the last 6 months.
Use this if you are a C/C++ developer experimenting with small to medium-sized neural networks or need to deploy models with minimal dependencies on CPU-only environments.
Not ideal if you need to train very large neural networks, require GPU acceleration, or depend on advanced features like batch normalization readily available in other frameworks.
Stars
746
Forks
121
Language
C
License
—
Category
Last pushed
Jun 06, 2025
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/attractivechaos/kann"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Related frameworks
Dobiasd/frugally-deep
A lightweight header-only library for using Keras (TensorFlow) models in C++.
flashlight/flashlight
A C++ standalone library for machine learning
NVlabs/tiny-cuda-nn
Lightning fast C++/CUDA neural network framework
KasperskyLab/knp
Kaspersky Neuromorphic Platform
wichtounet/dll
Fast Deep Learning Library (DLL) for C++ (ANNs, CNNs, RBMs, DBNs...)