🤖 Can a Computer Learn?

AI & Machine Learning Playground

Artificial Intelligence sounds like science fiction — but it's already in your phone, your Netflix recommendations, and your Instagram feed. See how a computer "learns" from examples.

DigiTech A-Level §2.1.2 CS A-Level Unit 5

🤔 What is AI?

Artificial Intelligence = a computer that can do tasks that normally need human intelligence — recognising faces, understanding speech, making decisions.

Machine Learning = a type of AI where the computer learns from examples instead of being given exact rules. You show it 1,000 photos of cats and dogs, and it figures out the difference itself.

🍕 Analogy: Traditional programming = giving someone a recipe. Machine learning = giving someone 100 pizzas and saying "figure out how to make these."
🧠

Train a classifier

A classifier sorts things into categories. Train one by giving it examples, then test if it can classify new items correctly.

📋 Training Data (examples the AI learns from)
🌲 Decision Tree (rules the AI learned)
📊

Types of Machine Learning

👩‍🏫
Supervised
AI learns from labelled examples — you tell it "this is a cat, this is a dog." Like a teacher marking homework.
📌 Image recognition, spam filters, medical diagnosis
🔍
Unsupervised
AI finds patterns on its own without labels — "these things seem similar, let me group them." Like sorting a messy drawer.
📌 Customer grouping, anomaly detection, recommendations
🎮
Reinforcement
AI learns by trial and error — it gets rewarded for good actions and punished for bad ones. Like training a dog with treats.
📌 Game-playing AI, self-driving cars, robotics
📝 Exam tip: The classifier you just trained uses supervised learning — you gave it labelled examples and it learned rules from them. The decision tree is one of the simplest ML models and is great for exams because you can draw and trace through it.