📄️ Table of contents
Free discovery course on Machine Learning in 6 lessons. Supervised versus unsupervised learning, which algorithm suits which problem, why features decide everything, how to evaluate a model honestly, and why models fail in production.
📄️ 1. The three families
Lesson 1 of the free Machine Learning course: the three families of learning, classification versus regression, what clustering can and cannot tell you, and how to decide which family a business problem belongs to.
📄️ 2. The algorithms
Lesson 2 of the free Machine Learning course: what each algorithm family is actually for, why gradient boosting is the default on tables, when linear models are the right answer, and why no algorithm is best everywhere.
📄️ 3. Features decide everything
Lesson 3 of the free Machine Learning course: what feature engineering is, why domain knowledge beats algorithm shopping, how to encode categories and dates, why scaling matters for some models, and the features you must never use.
📄️ 4. Evaluating honestly
Lesson 4 of the free Machine Learning course: train, validation and test splits, cross-validation, why you need a trivial baseline, choosing a metric that matches the cost of errors, and reading a confusion matrix.
📄️ 5. Why models fail
Lesson 5 of the free Machine Learning course: data leakage, unrepresentative training data, the training-serving gap, drift after deployment, and feedback loops where the model changes the world it predicts.
📄️ 6. Recap and FAQ
Lesson 6 of the free Machine Learning course: a one-page synthesis, a checklist for running a project from problem to monitoring, and answers to the 12 questions asked most about applied machine learning.
📄️ 7. Quiz and attestation
Test your understanding of machine learning with a free 5-question quiz, corrected and explained: supervised versus unsupervised, algorithm choice, feature engineering, evaluation splits and production failures.