Skip to content

Level 1 · Entry Foundations

Goal: build the working vocabulary and mechanical fluency you need before any ML course makes sense — vectors and matrices, what a derivative actually is, how gradients generalize derivatives to many variables, and how all of it comes together in the simplest real ML algorithm: linear regression.

Modules

  1. Why Math Matters for ML
  2. Scalars, Vectors & Matrices
  3. Vector Operations
  4. Matrix Operations
  5. Functions & Graphs Refresher
  6. What Is a Derivative?
  7. Basic Derivative Rules
  8. Partial Derivatives & Gradients
  9. Linear Regression as a Math Example
  10. Capstone — Derive & Verify a Gradient

By the end of this level you'll be able to read and write vector/matrix notation, take derivatives of simple and composite functions by hand, compute a gradient, and connect all of it to the cost function behind linear regression — with every hand-derived result checked in NumPy.