siekmanj/sieknet
A recurrent/memory-based neural network library implemented from scratch in C.
This is a low-level software library for building and running specific types of AI models, particularly those that learn from sequences or time-series data. It takes raw text or numerical environmental observations as input and can generate new text or control robotic behaviors. Developers who need to integrate AI capabilities into C-based applications, especially for resource-constrained environments, would use this library.
No commits in the last 6 months.
Use this if you are a C programmer building recurrent neural networks from scratch and need a lightweight, dependency-free library for tasks like text generation or basic reinforcement learning in environments like robotics simulations.
Not ideal if you are a researcher or practitioner using established deep learning frameworks (like PyTorch or TensorFlow) or if you need to implement convolutional neural networks or other non-recurrent architectures.
Stars
57
Forks
4
Language
C
License
AGPL-3.0
Category
Last pushed
May 21, 2021
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/siekmanj/sieknet"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
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...)