Nano Neural Net (NNN) is a simple implementation of a neural network written in Rust. Its primary goal is educational, aiming to demonstrate the principles behind neural networks through a small and understandable codebase. Whether you're a student delving into the world of machine learning, an educator looking for teaching materials, or just a curious mind, NNN provides the foundational blocks to construct and understand neural network architectures and their training processes.
NNN is built with Rust and currently has no dependencies beyond the standard library, making it straightforward to compile and run. However, to generate visual representations of the neural networks, you will need to have Graphviz installed on your system.
- Rust (latest stable version recommended)
- Graphviz (optional)
As NNN is still in the early stages of development, its usage is primarily oriented towards developers and contributors. The current functionality allows for the creation of simple neural network nodes and their visualization via Graphviz.
Note: This project is a work in progress (WIP). Future updates aim to provide user-friendly features for constructing neural network architectures and training them.
Contributions to Nano Neural Net are warmly welcomed. Whether it's adding new features, fixing bugs, or improving documentation, your help will make NNN a better educational tool for everyone.
If you're interested in contributing, please:
Check the open issues or create a new one describing the feature or fix you have in mind. Fork the repository and make your changes. Submit a pull request with a clear description of your changes. Let's build a great neural network learning tool together!
This project is licensed under the MIT License - see the LICENSE file for details.