Track
Math for ML
Goal: Linear algebra, calculus, probability, optimization.
Prereqs: none
Status: done
Work through the steps in order. Bold links open YouTube.
| Step | Concept | YouTube | Read |
|---|---|---|---|
| 1 | Vectors | 3Blue1Brown — Vectors | |
| 2 | Matrices as maps | 3Blue1Brown — Linear transformations and matrices | |
| 3 | Dot products | 3Blue1Brown — Dot products and duality | |
| 4 | Eigenvectors | 3Blue1Brown — Eigenvectors and eigenvalues | CS229 — Linear Algebra Review |
| 5 | Derivatives | 3Blue1Brown — The paradox of the derivative | |
| 6 | Chain rule | StatQuest — The Chain Rule | |
| 7 | Gradient descent | StatQuest — Gradient Descent, Step-by-Step | |
| 8 | Matrix calculus | The Matrix Calculus You Need For Deep Learning | |
| 9 | Bayes | StatQuest — Bayes’ Theorem | |
| 10 | Gaussians | StatQuest — The Normal Distribution | CS229 — Probability Theory Review |
Found a broken link or an unclear step? Report a problem with this track.