Chapter 6

Artificial Intelligence

AI lets machines mimic human thinking. Expert systems use a rule base and inference engine; machine learning improves from training data.

What is artificial intelligence?

Artificial intelligence (AI) is the ability of a computer system to carry out tasks that would normally need human intelligence, such as learning, reasoning and recognising patterns. An AI system collects data, uses stored knowledge or experience to make a decision, and can adapt its behaviour over time.

Expert systems

An expert system is a type of AI that stores the knowledge of human experts to give advice or make decisions in a narrow field, such as medical diagnosis. Its main parts are:

  • Knowledge base / rule base - a store of facts and IF...THEN rules.
  • Inference engine - the part that applies the rules to the facts to reach a conclusion.
  • User interface - lets the user enter information and read the advice.

Key idea

An expert system reasons using a rule base and an inference engine. Machine learning is different: it improves automatically by finding patterns in large amounts of training data, rather than following fixed rules.

Machine learning

In machine learning, a system is given a large set of training data and learns the patterns in it. The more good-quality data it sees, the better its predictions become. This is how systems recognise speech, translate languages or suggest products. A drawback is that poor or biased training data leads to poor decisions.

Example

An expert system for car faults might hold the rule "IF the engine will not start AND the lights are dim THEN check the battery." The inference engine matches the user's answers to this rule and advises checking the battery.

Stuck on this topic? A verified JomKelas tutor can walk you through it.

Find a verified tutor