Cambridge IGCSE 0478 · Topic 6 · 6.3

Artificial
Intelligence

Machine Learning · Expert Systems · Natural Language · Applications

CSZoneCambridge IGCSE Computer Science 0478

What is AI?

Machines That Learn & Reason

Artificial Intelligence (AI): the ability of a computer system to perform tasks that would normally require human intelligence — such as understanding language, recognising images, making decisions, or learning from experience.

Machine Learning (ML): AI systems trained on large datasets — they find patterns and improve over time without explicit rule-by-rule programming

AI does not mean the machine is truly conscious — it simulates intelligent behaviour based on data and algorithms

Expert Systems

AI That Applies Human Expertise

An expert system is an AI that mimics the decision-making of a human expert in a specific domain. It uses a knowledge base of rules and an inference engine to reach conclusions.

Components: Knowledge base (facts and IF-THEN rules) + Inference engine (applies rules to new input) + User interface (explains recommendations)

Examples: medical diagnosis systems, credit approval systems, fault-diagnosis in engineering

AI Applications

Where AI is Used Today

Natural Language Processing (NLP): voice assistants (Siri, Alexa), translation, chatbots — understanding and generating human language

Image & face recognition: security cameras, phone unlock, medical imaging analysis (cancer detection)

Recommendation systems: Netflix, Spotify, Amazon — learns preferences and suggests content

Self-driving vehicles: sensors + AI process road data and make driving decisions in real time

Exam Practice

Have a go at this question

Cambridge IGCSE 0478 style

Describe the main components of an expert system and explain how it reaches a conclusion for a user.

4 marks

The knowledge base stores facts and expert rules (IF-THEN statements) about a specific domain [1]. The inference engine applies these rules to data input by the user [1] to reach conclusions or recommendations [1]. An explanation interface shows the user how the conclusion was reached [1].

Key Takeaways

What to Remember

AI: systems that perform tasks needing human intelligence; ML: learns from data without explicit programming

Expert system = knowledge base (rules) + inference engine (applies rules) + user interface

Applications: NLP (voice assistants), image recognition, recommendations, self-driving cars

AI doesn't "think" — it pattern-matches based on training data and programmed rules