glouw/tinn
A 200-line dependency-free neural network library written in C99 with backpropagation training.
Not currently ranked — collecting fresh signals.
star history
Tinn is a minimal neural network implementation in C that provides forward and backward propagation for feedforward networks. It includes a single hidden layer architecture with sigmoidal activation and supports training on datasets like handwritten digits. The library is designed to be portable and lightweight, suitable for embedded systems after training on a more powerful desktop.
Frequently asked
- What is glouw/tinn?
- A 200-line dependency-free neural network library written in C99 with backpropagation training.
- Is tinn open source?
- Yes — glouw/tinn is open source, released under the MIT license.
- What language is tinn written in?
- glouw/tinn is primarily written in C.
- How popular is tinn?
- glouw/tinn has 2.1k stars on GitHub.
- Where can I find tinn?
- glouw/tinn is on GitHub at https://github.com/glouw/tinn.