Knowledge of basic concepts from calculus, linear algebra, probability theory, and statistics is essential for this course. In case you need to catch up on these topics, Part I of the “Deep Learning” book or “Mathematics for Machine Learning” serve as excellent resources. For a more comprehensive exploration, you can refer to relevant courses offered by MIT courses.

Whether a Data Scientist should be good at math or not – that’s a debatable question, I’d say a holy war. This post by Andrej Karpathy offers a good argument supporting math as a prerequisite for doing ML (and, well, understanding what you are doing).

Check the expression below (it’s from bonus assignment 8). If you are not comfortable with the idea of taking its derivative w.r.t. to \(w\), better refer to the resources listed above.