Home · IGCSE Computer Science 0478 · Automated and emerging technologies · Artificial intelligence: expert systems and machine learning · Practice
IGCSE · Practice questions · Artificial intelligence: expert systems and machine learning

Data, rules, reasoning.

Six original Cambridge-style questions on artificial intelligence, expert systems and machine learning, with worked solutions.

Original questions All questions on this page are original work, written in the Cambridge IGCSE style. They are not from past papers. They test the same concepts and skills the syllabus rewards.
Keep these straight

Use the syllabus words.

01
Recall
[1 marks]

State what is meant by artificial intelligence.

  • A branch of computer science dealing with the simulation of intelligent behaviours by computers. ✓
02
Recall
[3 marks]

Describe the main characteristics of an AI system.

  • It has a collection of data and rules for using that data. ✓
  • It has the ability to reason (apply the rules to the data to reach a conclusion). ✓
  • It can include the ability to learn and adapt (change its own data or processes). ✓
03
Explain
[4 marks]

An expert system is used to identify faults in washing machines. Identify the four components of the expert system and give the purpose of each.

  • Knowledge base: stores the facts about washing machines and their faults, gathered from experts. ✓
  • Rule base: stores the IF ... THEN rules for using the facts, e.g. IF the drum does not turn AND the motor hums THEN the belt may be broken. ✓
  • Inference engine: applies the rules to the facts and the user's answers to reach a diagnosis, and chooses the next question. ✓
  • Interface: asks the user questions and displays the likely fault (and its probability / the reasoning). ✓
04
Explain
[5 marks]

A technician uses an expert system to find the fault in a washing machine. Describe how the expert system is used to reach a diagnosis.

  • The interface asks the technician a question about the machine (e.g. does the drum turn?). ✓
  • The technician enters an answer (e.g. yes/no) through the interface. ✓
  • The inference engine searches the knowledge base using the rules in the rule base. ✓
  • It uses the answers so far to decide the next question, and the questions and answers repeat. ✓
  • The interface outputs the most likely fault, often with a probability and an explanation of the reasoning. ✓
05
Explain
[2 marks]

Explain what is meant by machine learning, using an example.

  • A program can automatically adapt its own processes and/or data (without being reprogrammed). ✓
  • Example: a spam filter updates itself each time a user marks an email as spam, so it blocks similar emails in future (or any valid example such as recommendations or speech recognition). ✓
06
Analysis
[2 marks]

A bank uses software to spot fraudulent card payments. Over time it becomes better at telling unusual payments from normal ones, without a programmer changing the code. State whether this is an expert system or machine learning, and justify your answer.

  • Machine learning. ✓
  • The software automatically adapts its own processes/data from new payment data and feedback; an expert system's rules only change when people update them. ✓

Mark this once you have attempted all six and checked your working. It records a Practiced badge on the topic and adds a one-time bonus. Revealing the solutions alone does not count.