This is a repository that contains implementations of various machine learning models from scratch and the implementations are written in plain Python and NumPy, or PyTorch.
The Machine-Learning-Implementation repository is intended for learning more about the inner workings of machine learning models or use bare-bones implementations for their own projects. Also, they allow for a deeper understanding of the underlying algorithms and techniques.
Each implemented model is self-contained, developed and tested in Google Colab, making it easy to experiment and learn in a cloud-based environment. Additionally, these implementations can also be seamlessly used in local Jupyter notebooks for further exploration and development.
Here are the models that have been implemented so far:
- Linear Regression - (Python and NumPy)
- Logistic Regression - (Python and NumPy)
- K-Nearest Neighbors (KNN) - (Python and NumPy)
- Naive Bayes - (Python and NumPy)
- Neural Networks - (Python and NumPy)
- Neural Networks - (PyTorch)
- Convolutional Neural Networks (CNN) - (PyTorch)
More models will be added in the future.
This project is licensed under the MIT License - see the LICENSE.md file for details.