← IGCSE Computer Science Paper 1

Machine learning

A type of AI where a program automatically adapts its own processes and/or data, improving with experience, with no programmer changing it.

Part of: IGCSE Computer Science 0478 — 6.3 Artificial Intelligence — Module 18

Understanding Machine learning in IGCSE Computer Science Paper 1

What it does: The pseudocode shows performance rising after the program learns from new data, which is how machine learning improves with experience. Machine learning sits inside the wider field of AI. It is one of the two types of AI in this course, alongside expert systems. Automatic means no programmer has to make the change. The program adapts on its own. The syllabus wording is that it adapts its own processes and/or data. Hardware is not part of this.

Common mistakes: A machine learning program adapts its own data as it sees new examples. It should ADD the spam email to spamData, not remove it, so the filter improves with experience. The function call is missing its closing bracket. It should be result ← playRound().

Class: _____________________ · Name: _____________________ · Date: _________

Free printable worksheet with full answer key — or add this module to a class and your students practise it interactively.

🖨 Print worksheet + answer key Add Machine learning to a class →

This module's key terms are also in a printable crossword (Modules 662–678) and word search (Modules 652–678).

Take this worksheet further — free with Cloodit

Each concept is reinforced from every angle — learned, then applied, then tested.

Learning

Duo

Which statement matches the syllabus wording for machine learning?

A program that only follows fixed instructions written by a programmerA program has the ability to automatically adapt its own processes and/or data

Matches

A programmer edits the rules each week to make the system learn

↓

This is not machine learning because a programmer is making the changes. In machine learning the adaptation is automatic.

Applying

Meanings

Term

machine learning

Meaning

A type of AI where a program automatically adapts its own processes and/or data, improving with experience, with no programmer changing it.

Practice

WHILE experience < 100

Testing

Gaps

Machine learning is a type of

Check Answer

Spots

2 IF label = 'spam' THEN

3 REMOVE email FROM spamData

Cloodit turns curriculum-aligned coding content into journeys students work through one biome at a time.

Students earn collectable badges

Over 100 of them, across seven natural biomes.

Study Buddy

Students build a real study resource

Turns their work into revision material ready for Flash Cards and Exam study.

Diamond Dash — one of Cloodit's live, competitive Sprint games

Students lock in with Sprints

Live, competitive practice for the start of the lesson or a teacher-led lesson finisher.

A Cloodit certificate of achievement, ready to personalise and print

Custom printable certificates

Honour your top performers, or encourage a student who's trying hard — ready to print in seconds.

Add to class →

Quick Questions

1. Which statement matches the syllabus wording for machine learning?

A. A program has the ability to automatically adapt its own processes and/or data ✓

B. A program that only follows fixed instructions written by a programmer

The syllabus says machine learning is the ability to automatically adapt its own processes and/or data.

2. In machine learning, what does 'automatic' mean?

A. A programmer rewrites the code each time it needs to change

B. The program changes itself without a programmer editing it ✓

Automatic means no programmer has to make the change. The program adapts on its own.

3. A spam filter gets better at spotting junk email the more emails it sees. What is this an example of?

A. A program improving with experience ✓

B. A program with fixed rules that never change

Improving with experience is a key idea of machine learning.

4. Machine learning is best described as...

A. A type of computer hardware

B. A type of AI ✓

Machine learning is a type of artificial intelligence, alongside expert systems in this course.

5. Which of these can a machine learning program adapt by itself?

A. Its own processes and/or its own data ✓

B. Only the physical parts of the computer

The syllabus wording is that it adapts its own processes and/or data. Hardware is not part of this.

Match the Pairs

machine learning → A type of AI where a program automatically adapts its own processes and/or data

automatic adaptation → The program changes itself with no programmer editing the code or data

A machine learning program improves with experience as it gets more data → accuracy = accuracy + learned_from(new_data)

Machine learning is a type of AI, so it is one way a system can show intelligent behaviour → ML ⊂ AI

A programmer edits the rules each week to make the system learn → This is not machine learning because a programmer is making the changes. In machine learning the adaptation is automatic.

A program gives the same output however much experience it gets: machine learning → A program that never changes its processes or data does not improve with experience, so it is not machine learning.

Key Term

machine learning

A type of AI where a program automatically adapts its own processes and/or data, improving with experience, with no programmer changing it.

Fill in the Blanks

1. Machine learning is a type of AI

Hint: Type the abbreviation for the wider field that machine learning belongs to.

2. Machine learning adapts its own processes and/or data

Hint: Type the word for the steps a program follows, which machine learning can change by itself.

3. A program that adapts automatically with no programmer changing it

Hint: Type the adverb meaning the change happens without a person making it.

4. A program that improves with experience

Hint: Type the word for what the program gains from past use, which makes it get better.

5. Machine learning adapts its own processes and/or data

Hint: Type the other thing, besides processes, that a machine learning program can change by itself.

Spot the Error

Question 1

A FUNCTION learn(email, label)

B IF label = 'spam' THEN

C REMOVE email FROM spamData

D ENDIF

E ENDFUNCTION

Line C — A machine learning program adapts its own data as it sees new examples. It should ADD the spam email to spamData, not remove it, so the filter improves with experience.

Question 2

A WHILE playing = TRUE

B result ← playRound(

C IF result = LOSS THEN

D adjustOwnRules()

E ENDIF

F ENDWHILE

Line B — The function call is missing its closing bracket. It should be result ← playRound().

Question 3

A experience ← 0

B REPEAT

C experience ← experience + 1

D accuracy ← accuracy - 0.1

E UNTIL experience = 100

Line D — Machine learning improves with experience, so accuracy should go up as experience grows. It should be accuracy + 0.1, not minus.

Question 4

A READ newData

B WAIT FOR programmer TO EDIT

C OUTPUT 'Rules updated'

Line B — In machine learning the adaptation is automatic: no programmer changes the rules. The program should update its own rules using the new data.

Question 5

A FOR each photo IN trainingSet

B guess ← label

C IF guess <> label THEN

D improveModel()

E NEXT photo

Line B — The guess must come from the model's own prediction. Copying the correct label means the model never makes a mistake, so it has nothing to learn from. It should be guess ← predict(photo).

Student with a class code? Join your class →