L1
Honest Take — Before You Begin
This is the module most people quit on. I need to be honest about that.
preview →
You need to sign in or sign up before continuing.
Course · 6 lessons
~98 hr
Advanced
Mathematical Foundations for ML
Mathematical Foundations for ML covers: A Programmer's Introduction to Mathematics, Essential Math for Data Science, Mathematics for Machine Learning. Build the math you need to understand ML, not to become a mathematician. You need linear algebra (vectors, matrices, transformations), calculus (derivatives, gradients, optimization), and probability/statistics. Think of this module like understanding database internals. You used ActiveRecord for years without knowing how B-trees or query planners work. Then you learned, and suddenly index design and query optimization made deep sense. This module does the same thing for ML — you will go from "sklearn.fit() magic" to "I know exactly what is happening inside."
reading · we frame, you read MIT or the canonical
taught · we author, no canonical fits
↺ spirals back to earlier lessons
Course locked
Complete Python as an ML Tool first.
This course unlocks once you've finished its prerequisite. Open prerequisite →
L2
A Programmer's Introduction to Mathematics: The Warm-Up Lap
Try reading this: f: ℝ² → ℝ. If your eyes slid off it the way they slide off a minified JavaScript bundle, you have found the actual gap between you and machine learning. It is no…
primary
3Blue1Brown: Essence of Linear Algebra
locked
L3
Essential Math for Data Science: Where the Math Meets the Data
There is a moment in every Rails engineer's ML journey where the math stops being homework and starts being leverage. It usually is not in a proof. It is the first time you look a…
primary
3Blue1Brown: Essence of Linear Algebra
locked
L4
Mathematics for Machine Learning: The Canonical Text, Earned
Somewhere in the first pages of this book's linear algebra chapter, you will meet the formal definition of a vector space — a set, two operations, and eight axioms that all must h…
primary
3Blue1Brown: Essence of Linear Algebra
locked
L5
Module Checklist
Work through each item before the checkpoint.
locked
L6
Project: Gradient Descent from Scratch
The algorithm underneath all of deep learning, built by hand: compute a loss, compute its gradient, step downhill, repeat. You'll implement linear regression's gradients, verify t…
locked
6 lessons. Read in order; spiral back when you need to. By the end you'll have used the core ideas twice — once on the abstract, once on something you'll meet at work next week.