Micro Free Course — 100% Free Learning
All lessons in this module are free to learn. Sign in with Google to save your progress.
ML Foundations: The Mental Model
What ML is and isn't, supervised vs unsupervised, the bias-variance tradeoff, train/validation/test discipline, and cross-validation. The mental model before any library.
Module Content
What ML Is (and Isn't) — A Practical Definition
ML is statistical pattern recognition. Knowing what it isn't (magic, AGI, causality) is half the value. FIND_VIDEO: search 'machine learning vs statistics vs AI' — recommended channel: StatQuest / Andrew Ng. Aim for 10 min or under.
Quiz: Supervised, Unsupervised, and Where Each Fits
Practice quiz: The three families of ML, and the kinds of problem each one solves. The mental model that organizes the rest of this course.
The Bias-Variance Tradeoff
Why models can be 'too simple' or 'too complex' — and what to do when you suspect one. FIND_VIDEO: search 'bias variance tradeoff explained' — recommended channel: StatQuest. Aim for 10 min or under.
Quiz: Underfitting vs Overfitting in Practice
Practice quiz: The bias-variance decomposition explains why your model can be wrong in two opposite ways.
Train/Validation/Test — The Three-Split Discipline
The single piece of ML discipline that separates honest models from theatre. FIND_VIDEO: search 'train validation test split machine learning' — recommended channel: StatQuest / Andrew Ng. Aim for 10 min or under.
Quiz: Why You Need All Three Sets
Practice quiz: Two sets isn't enough. The third set is what makes your final accuracy number trustworthy.
Cross-Validation — When Data is Scarce
Make every row count. K-fold and its variants for robust evaluation. FIND_VIDEO: search 'cross validation k-fold stratified' — recommended channel: StatQuest. Aim for 10 min or under.
Quiz: K-Fold, Stratified, Time-Based CV
Practice quiz: The cross-validation variants and when each one is right. Plus the trap of CV at the wrong granularity.
SUBMISSION: Milestone Project 1 — Problem Formulation: Framing a Real Business Problem as an ML Task
Turn a vague retention complaint at a D2C subscription business into a leakage-free ML task: label definition, observation windows, success metric, and a costed baseline plan.