wayground logo

Free Printable Worksheets

NEW

Font size

S
M
L
XL
Worksheets

12B,D,E final revision

Total questions: 50

Worksheet time: 25mins

Name
Class
Date
1.

What is the main goal of Artificial Intelligence (AI)?

a)

To store large amounts of data

b)

To help machines think and make decisions like humans

c)

To make computers larger and faster

d)

To reduce the number of computer programs needed

2.

Machine learning allows computers to:

a)

Memorize all data without understanding

b)

Learn from data and make predictions

c)

Write code automatically

d)

Never make mistakes

3.

Which of the following is a dataset?

a)

A single number

b)

A collection of data used to train or test a model

c)

A programming language

d)

A website

4.

A feature is:

a)

A value used to make predictions

b)

A final prediction

c)

A programming function

d)

The label

5.

A label is:

a)

The dataset’s title

b)

The value the model is trying to predict

c)

The number of features

d)

A programming command

6.

Supervised learning uses:

a)

Labeled data

b)

No labels

c)

Random guessing

d)

Predictions only

7.

Unsupervised learning uses:

a)

Labeled data

b)

Data without labels

c)

Only numbers

d)

Only text

8.

Classification models:

a)

Predict categories

b)

Predict numerical values

c)

Delete features

d)

Create datasets

9.

Which is a classification task?

a)

Predicting the number of apples in a basket

b)

Deciding whether a photo shows a cat or dog

c)

Calculating the sum of numbers

d)

Measuring temperature

10.

Regression models:

a)

Group data into categories

b)

Predict numerical values

c)

Ignore features

d)

Make random predictions

11.

Training a model means:

a)

It learns patterns from data

b)

Testing it on new data

c)

Deleting data

d)

Random predictions

12.

Testing a model means:

a)

Training it further

b)

Checking its accuracy on new data

c)

Adding features

d)

Removing labels

13.

Bias occurs when:

a)

Data is balanced

b)

Data is incomplete or unrepresentative

c)

Model predicts correctly

d)

Features are too many

14.

Example of supervised learning:

a)

Grouping customers without labels

b)

Classifying emails as spam or not

c)

Random number generation

d)

Sorting numbers alphabetically

15.

Example of unsupervised learning:

a)

Predicting house prices

b)

Grouping customers by buying behavior without labels

c)

Classifying emails

d)

Predicting exam scores

16.

Patterns in data help models:

a)

Memorize the dataset

b)

Make predictions

c)

Randomize outputs

d)

Delete features

17.

Multiple features in a dataset:

a)

Confuse the model

b)

Give more information to improve predictions

c)

Increase file size unnecessarily

d)

Slow down training

18.

Labeling data provides:

a)

Correct answers for the model

b)

Extra features

c)

Random guesses

d)

Larger datasets

19.

Real-life example of AI:

a)

Chess-playing program

b)

Visual impairment app

c)

Email spam filter

d)

All of the above

20.

A good dataset should be:

a)

Small and incomplete

b)

Large, diverse, and representative

c)

Random without relevance

d)

Only one type of example

21.

AI can help humans by:

a)

Automating repetitive tasks

b)

Supporting decision-making

c)

Predicting trends from data

d)

All of the above

22.

Features can be:

a)

Numbers, text, or categories

b)

Only numbers

c)

Only images

d)

Only text

23.

A model’s prediction depends on:

a)

Features and patterns in data

b)

Random numbers

c)

The size of the computer

d)

The number of labels only

24.

Patterns in data are important because:

a)

They reduce dataset size

b)

They allow models to learn and predict

c)

They make data more colorful

d)

They increase memory usage

25.

Labeling is necessary for:

a)

Unsupervised learning

b)

Supervised learning

c)

Random guessing

d)

Testing only

26.

AI can fail if:

a)

Data is biased or incomplete

b)

Model is simple

c)

Features are missing

d)

All of the above

27.

Evaluating a model helps to:

a)

Increase features

b)

Improve accuracy and detect bias

c)

Reduce dataset size

d)

Delete labels

28.

Bias can cause:

a)

Fair predictions

b)

Unfair or inaccurate predictions

c)

More features

d)

Larger datasets

29.

A dataset with missing values can:

a)

Improve model accuracy

b)

Reduce model accuracy

c)

Increase bias automatically

d)

Make the model unsupervised

30.

AI examples in daily life include:

a)

Voice assistants

b)

Self-driving cars

c)

Recommendation systems

d)

All of the above

31.

Which of these is a common step in machine learning?

a)

Training

b)

Testing

c)

Evaluating

d)

All of the above

32.

A feature is important because it:

a)

Determines what the model can learn from

b)

Is always the predicted value

c)

Reduces dataset size

d)

Is optional

33.

Which of these is supervised learning?

a)

Grouping customers by behavior

b)

Predicting stock prices from historical data

c)

Both A and B

d)

None of the above

34.

Which of these is unsupervised learning?

a)

Clustering customers based on purchasing habits

b)

Predicting tomorrow’s temperature

c)

Classifying emails as spam

d)

Counting students in class

35.

A classification model predicts:

a)

Categories

b)

Numbers

c)

Text only

d)

Images only

36.

A regression model predicts:

a)

Categories

b)

Numerical values

c)

Labels only

d)

Features only

37.

Patterns in data allow models to:

a)

Memorize data exactly

b)

Make predictions on new data

c)

Ignore new inputs

d)

Delete labels

38.

Evaluating a model helps to:

a)

Detect errors or bias

b)

Delete features

c)

Memorize the dataset

d)

Make predictions random

39.

An example of AI improving lives is:

a)

A recommendation system for movies

b)

A voice assistant like Siri

c)

Self-driving car software

d)

All of the above

40.

Bias in AI can be caused by:

a)

Incomplete data

b)

Data that is not diverse

c)

Ignoring certain features

d)

All of the above

41.

A model card is used to:

a)

Represent information about a trained model

b)

Delete a dataset

c)

Add features automatically

d)

Train the model faster

42.

Supervised learning requires:

a)

Labeled data

b)

Unlabeled data

c)

Random guessing

d)

No data

43.

Unsupervised learning requires:

a)

Labeled data

b)

Unlabeled data

c)

Random guesses

d)

Predefined predictions

44.

Classification vs Regression:

a)

Both predict categories

b)

Classification predicts categories, regression predicts numbers

c)

Regression predicts categories, classification predicts numbers

d)

Both predict numbers

45.

Features can be:

a)

Age, height, color, or category

b)

Only numbers

c)

Only letters

d)

Only images

46.

A model makes predictions based on:

a)

Patterns in training data

b)

Random numbers

c)

File size

d)

Number of labels only

47.

Which is an example of classification?

a)

Deciding whether a customer will buy a product or not

b)

Predicting the total sales amount

c)

Counting items in inventory

d)

Measuring temperature

48.

Which is an example of regression?

a)

Predicting tomorrow’s temperature

b)

Sorting fruits into categories

c)

Detecting spam emails

d)

Grouping customers

49.

Patterns help a model because:

a)

They allow predictions on new data

b)

They increase file size

c)

They reduce accuracy

d)

They delete features

50.

Evaluating a model ensures:

a)

It works accurately and fairly

b)

It deletes data automatically

c)

It adds random features

d)

It ignores bias