The four ways machines learn
Supervised learning uses labeled examples. Unsupervised learning seeks structure without those labels. Semi-supervised learning combines labeled and unlabeled examples. Reinforcement learning uses rewards. LLM pretraining commonly uses self-supervised prediction; later training can use supervised examples and reinforcement learning.
AI models must be taught before they can solve anything. Machine learning is that teaching process. Four approaches, one comparison table, then the detail the exam digs into.
| Approach | Training data | Goal | Examples | Watch-outs |
|---|---|---|---|---|
| Labelled data, inputs mapped to known targets | Predict outputs for new, unseen data | Spam detection, fraud flagging, labelled road signs | Labelled data is costly and slow, labelling can introduce bias | |
| Unlabelled data, no predefined targets | Find hidden patterns, structures, relationships | Customer segmentation, anomaly detection, genetics, fault detection, marketing | Cheaper but less accurate, unpredictable, interpretation is subjective | |
| Small labelled + large unlabelled set | Best of both worlds, cuts manual labelling cost | Speech recognition, LLMs often rely on it, ChatGPT, DALL-E | Label quality and consistency, choosing an algorithm that handles both data types | |
| No labels → an agent interacts with an environment | Maximise reward through trial and error | Game AI, robots in mazes/warehouses, AVs, predictive text, real-time ad bidding | Designing the reward mechanism, exploration vs exploitation trade-off |
Inside supervised learning - two sub-types. Classification models predict specific categorical responses by labelling input data (e.g. "Spam" vs "Not spam", image recognition, medical diagnosis); is used mostly for classification. Regression models predict a continuous numerical outcome (e.g. car price, stock prices, temperature); most commonly produces continuous values.
Inside unsupervised learning - two sub-types. Clustering automatically groups data points sharing similar attributes (e.g. DNA samples, customer segments). Association rule learning identifies relationships between data points (e.g. people who buy X also buy Y).
An agent acts in an environment → rewarded actions get reinforced, errors trigger penalties proportional to the error's scale. The agent is never told what to do, it learns from trial and error. Real deployment → Amazon's warehouse supply chain optimisation.
Read the actual training setup. Labeled examples suggest supervised learning. A mixture of labeled and unlabeled examples suggests semi-supervised learning. Predicting labels derived from the input itself is self-supervised learning. Do not classify every LLM training stage as semi-supervised.
Key terms - quick answers
What is “Supervised learning”?
What is “Unsupervised learning”?
What is “Semi-supervised learning”?
What is “Reinforcement learning”?
Sources and study method
This independent lesson uses active recall, spaced retrieval and scenario practice. Read the full study method.