Machine Learning (ML)

Machine Learning is the capability of computer to adapt to new circumstances and to detect and extrapolate patterns¹, under Acting Humanly definition of Artificial Intelligence.

There are three branches of ML²:

• Supervised learning
• Unsupervised learning
• Reinforced learning

Supervised learning

ML approach where an algorithm learns from labelled training data. Requires data reflecting situations with known outcomes.

An example of self-supervised learning is Large Language Models (LLMs).

Unsupervised learning

Models of this ML approach learn from unlabeled data.

Reinforced learning

Agents acting in this approach learn to make decisions and take actions in an environment to achieve a goal, where rewards or penalties are received based on actions, in order to learn to maximise rewards over time.

---

1. Russell, S. J., Norvig, P. & Davis, E. Artificial Intelligence: A Modern Approach. (Prentice Hall, Upper Saddle River, 2010) ↩︎

2. xUnlocked: Introduction to Data and AI (2025). ↩︎