Recoding Core Machine Learning Concepts in Numpy

Synopsis

In order to understand the details of the most frequent algorithms in Machine Learning, I have recoded the core concepts in Python using only Numpy (for computations) and Matplotlib (for visualizations).

Table of content

Gradient Descent Regressor: Python script | Detailed explanations
Logistic Regression: Python script
Logistic Regression Image Classifier: Jupyter notebook | Detailed Explanations
Shallow Neural Network: Jupyter notebook | Detailed Explanations

Built with

NumPy
Matplotlib

Author

Gavin Bauer - Data Analyst of 5+ years experience | Current: 🦉@KeringGroup | Past: ⚡@Total, 🌱@YvesRocherFR

License

This code is licensed under the MIT License - see the LICENSE file for details

Acknowledgements | Inspiration

Andrew Ng's amazing Machine Learning course
Emil Wallner's post The History of Deep Learning