A neural network library built from scratch.
Project description
BareBonesNN is a lightweight neural network library implemented from scratch in Python, without relying on high-level machine learning libraries. This project aims to provide a clear and fundamental understanding of neural network concepts and operations, making it an excellent educational resource for learning and experimentation.
## Features
Basic Neural Network Components: Core classes including Value, Neuron, Layer, and MLP (Multi-Layer Perceptron).
Automatic Differentiation: Built-in backpropagation for gradient computation.
Customisable and Extensible: Easily modify and extend the code to experiment with various neural network architectures.
Lightweight: Minimal dependencies, focusing on core principles.
## Installation
To install BareBonesNN, clone the repository:
`bash git clone https://github.com/yourusername/BareBonesNN.git cd BareBonesNN `
## Contributing
Contributions are welcome! If you have suggestions, bug reports, or feature requests, please open an issue or submit a pull request.
## License
This project is licensed under the MIT License - see the [LICENSE](LICENSE) file for details.
Project details
Release history Release notifications | RSS feed
Download files
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.
Source Distribution
Built Distribution
Hashes for barebonesnn-0.1.0-py3-none-any.whl
Algorithm | Hash digest | |
---|---|---|
SHA256 | 539c00b6d787e17f71b6c68d7160ebe30a3018b8256bef5bb3190ed14db943ff |
|
MD5 | 2e421aa3b55d4a7fdcdedf811f5dd3d6 |
|
BLAKE2b-256 | 27e7496777a1d15aa89949ac78407397db176a41f4aaa69f79532c4eb97f3076 |