Phase 3 · Machine learning · Foundations
What machine learning is
Programs that learn rules from examples instead of being told them.
Why it matters
You've been using machine-learned models all through Phase 1; this phase opens the box on the classic ones. They still run most of marketing's quiet infrastructure: churn prediction, lead scoring, lifetime value, fraud flags, recommendations. They're also the clearest way to learn the ideas that carry over to deep learning and LLMs: training data, generalization, overfitting and honest evaluation.
What you'll be able to do
- Contrast writing rules by hand with learning them from examples
- Name the main kinds of learning: supervised, unsupervised, self-supervised and reinforcement
- Judge when machine learning is worth it, and when a rule is better
- See 'learning' as searching for the settings that make the fewest mistakes
Before this lesson
Next in this phase: Features and labels