AIGP Study Guide
Module 8: AI Governance Vocabulary

Machine learning families

The four learning paradigms plus the architecture they run on. Label availability is the sorting key: supervised uses labelled pairs, unsupervised finds structure in unlabelled data, semi-supervised blends both, and reinforcement learning optimises for reward.

Machine learning is the AI subset where systems learn patterns from data to improve at tasks without being explicitly programmed rule by rule. The output of that learning is the Machine learning model - the trained artifact of learned parameters and logic. The four paradigms differ on one axis above all: how much of the data is labelled.

The four learning paradigms by label availability
ParadigmDataWhat it produces
Supervised learningLabelled input-output pairsClassification and regression
Unsupervised learningUnlabelled dataClustering and association (hidden structure)
Semi-supervised learningSmall labelled set + large unlabelled setWhere the course files LLMs
Reinforcement learningReward and penalty signalsPolicy learned by trial and error
  • Reinforcement learning with human feedback (RLHF) is RL whose reward signal is human preference ratings - the alignment step that makes outputs helpful and appropriate.
  • Deep learning is ML built on many-layered Neural networks that learn hierarchical representations - the engine behind generative AI.
Sorting key

When a scenario asks which paradigm fits, ask first: are the examples labelled? Labelled → supervised; none → unsupervised; a few → semi-supervised; rewards instead of labels → reinforcement.

Key terms - quick answers

What is “Machine learning”?
AI subset where systems learn patterns from data without explicit rule-by-rule programming.
What is “Machine learning model”?
Trained artifact of learned parameters/logic used to predict on new inputs.
What is “Supervised learning”?
Training on labelled input-output pairs (classification and regression).
What is “Unsupervised learning”?
Training on unlabelled data to surface hidden structure (clustering, association).