Starting from the very basics, we cover all of the most important ML algorithms and how to apply them in practice.
One new idea we tried in this course was to make all the materials executable. The slides are also Jupyter notebooks with programmatically generated figures. Readers can tweak parameters and regenerate the figures themselves.
Also, whenever we introduce an important mathematical formula, we implement it in numpy. This helps establish connections between the math and how to apply it in code.
Another idea we tried was to include 3 full lectures on how to apply ML in practice in a principled way. This includes topics such as how to prioritize model improvements, diagnose overfitting, perform error analysis, visualize loss curves, etc.
