← IGCSE Computer Science Paper 1

Machine learning adapting its own processes

A machine learning program changes its own processes, meaning how it makes decisions, using what happened before, so no human has to rewrite the code.

Part of: IGCSE Computer Science 0478 — 6.3 Artificial Intelligence — Module 19

Understanding Machine learning adapting its own processes in IGCSE Computer Science Paper 1

What it does: The program assigns new rules to itself from past_results, so it changes its own decision process without a human editing the code. A wrong result triggers adjust(rules) inside the program, which shows it adapting its own processes after a mistake. Machine learning adapts. It uses what happened before to change how it makes decisions, with no human rewriting the code. Here, processes means how the program makes decisions. The hardware stays the same. Adapting lets the program improve over time. It can still make mistakes, but it learns from them.

Common mistakes: After a wrong result the program should adjust its own rule using that result, for example rule ← adjust(rule, result). Setting it to a fixed rule means nothing is learned. A FOR loop needs the keyword TO between the start and end values. It should be FOR game ← 1 TO 100, so the program can play 100 games and keep learning.

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 adapting its own processes 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
A machine learning program finds that its last decision was wrong. What does it do next?
It changes its own processes so it decides better next timeIt keeps the same process and waits for a human to rewrite the code
Matches
A programmer must rewrite the code every time a machine learning program improves.
↓
Machine learning programs change their own processes using past data, so no human has to rewrite the code each time.
Applying
Meanings
Term
adaptive processes
Meaning
A machine learning program changes its own processes, meaning how it makes decisions, using what happened before, so no human has to rewrite the code.
Practice
FOR game \u2190 1 TO 1000
Testing
Gaps
IF result = "wrong"
Check Answer
Spots
2IF guess ≠ result THEN
3 rule ← fixed_rule

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

The 'Chambered Nautilus' badge — File Explorer, one of Cloodit's 106 collectible badges
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. A machine learning program finds that its last decision was wrong. What does it do next?
A. It changes its own processes so it decides better next time ✓
B. It keeps the same process and waits for a human to rewrite the code
Machine learning adapts. It uses what happened before to change how it makes decisions, with no human rewriting the code.
2. Who changes the decision-making rules when a machine learning program improves?
A. The program changes its own rules ✓
B. A programmer must rewrite the code each time
A key feature of machine learning is that no human has to rewrite the code. The program adjusts itself.
3. A chess program loses a game and then plays a different strategy in the next game because of what it learned. Which statement describes this?
A. The program is following a fixed set of rules that never change
B. The program improved its strategy by learning from past results ✓
A game program that improves its strategy from earlier games is adapting its own processes. That is machine learning.
4. Which one is an example of a machine learning program adapting its own processes?
A. A calculator always adds numbers using the same steps
B. A game program adjusts its moves after losing, using the results of earlier games ✓
A calculator follows fixed steps. A game program that changes its moves from past results is adapting.
5. What does 'processes' mean in 'a machine learning program can change its own processes'?
A. The way the program makes its decisions ✓
B. The physical parts inside the computer
Here, processes means how the program makes decisions. The hardware stays the same.

Match the Pairs

if guess_was_wrong: update_rules() → After a wrong result, the program changes its own rules so it decides better next time.
strategy = improve(strategy, game_history) → A game program uses what happened in earlier games to improve its own strategy.
A machine learning program changes how it makes decisions using what happened before, with no human rewriting the code. → rules = learn_from(past_results)
After a wrong result, the program adjusts its own rules instead of waiting for a programmer. → if result != correct: adjust(rules)
A programmer must rewrite the code every time a machine learning program improves. → Machine learning programs change their own processes using past data, so no human has to rewrite the code each time.
A game program keeps the same strategy and ignores what happened in earlier games. → A machine learning game program uses earlier results to change and improve its strategy, so ignoring them is not adaptive.

Key Term

adaptive processes
A machine learning program changes its own processes, meaning how it makes decisions, using what happened before, so no human has to rewrite the code.

Fill in the Blanks

1. IF result = "wrong" THEN score ← score - 1 ENDIF
Hint: Type the keyword that starts the block of code to run when the test is true, so the program can adjust after a wrong result.
2. IF result = "win" THEN score ← score + 1 ENDIF
Hint: Type the arithmetic operator that makes a rule's score go up after a good result.
3. IF score < 0 THEN DISCARD(rule) ENDIF
Hint: Type the comparison operator that checks whether the score has fallen below zero, so the program can drop a bad rule by itself.
4. FOR game ← 1 TO 1000 result ← PlayGame(strategy) strategy ← Adjust(strategy, result)
Hint: Type the keyword that starts a count-controlled loop, so the game program can practise many times and learn.
5. strategy ← Adjust(strategy, result) PRINT("Strategy updated") PRINT("No human edited the code")
Hint: Type the pseudocode assignment symbol that stores the new, adjusted strategy in the variable.

Spot the Error

Question 1
A guess ← predict(game_state)
B IF guess ≠ result THEN
C rule ← fixed_rule
D ENDIF
Line C — After a wrong result the program should adjust its own rule using that result, for example rule ← adjust(rule, result). Setting it to a fixed rule means nothing is learned.
Question 2
A FOR game ← 1 100
B move ← pick(strategy)
C result ← play(move)
D strategy ← learn(result)
E NEXT game
Line A — A FOR loop needs the keyword TO between the start and end values. It should be FOR game ← 1 TO 100, so the program can play 100 games and keep learning.
Question 3
A WHILE games < 50
B result ← play(strategy)
C games ← games + 1
D strategy ← update(games)
E ENDWHILE
Line D — The strategy must change based on what happened, which is the result of the game. It should be update(result), not update(games). The number of games played does not show what worked.
Question 4
A prediction ← model(email)
B IF prediction = label THEN
C model ← adjust(model)
D ENDIF
Line B — The program should change its own decision process when its prediction was wrong. The condition should be prediction ≠ label, not =, which would adjust when it was already right.
Question 5
A error ← target - output
B step ← 0.1 * error
C weight ← step
D OUTPUT weight
Line C — The weight should be adjusted a little using the old value, so it should be weight ← weight + step. Writing weight ← step throws away everything learned before.

Student with a class code? Join your class →