AI/ML Foundations
Supervised, Unsupervised & Reinforcement Learning
The major learning paradigms differ by feedback signal: supervised learning has labeled answers, unsupervised learning discovers structure, reinforcement learning learns from rewards, and self-supervised learning creates training targets from raw data itself.
- Supervised learning: examples come with targets
- Unsupervised learning: there is no target label
- Reinforcement learning: actions are judged by rewards over time
- Self-supervised learning: labels are manufactured from the data
- Feedback signal determines the evaluation plan
| Paradigm | Feedback | Output | Example |
|---|---|---|---|
| Supervised | Known labels/targets | Predictor | Classify support ticket intent |
| Unsupervised | No labels | Structure | Cluster customers by behavior |
| Self-supervised | Targets derived from raw data | Representation / generator | Next-token pretraining |
| Reinforcement | Reward from actions | Policy | Game-playing agent |