wayground logo

Free Printable Worksheets

Font size

S
M
L
XL
Worksheets

02_CS_3 Final Exam

Total questions: 90

Worksheet time: 45mins

Name
Class
Date
1.

Which of the following is a common method for collecting data to train AI models?

a)

Data mining

b)

Data painting

c)

Data erasing

d)

Data hiding

2.

What is the main purpose of data preprocessing in AI model training?

a)

To delete all data

b)

To clean and organize data

c)

To make data more confusing

d)

To hide data from the model

3.

Which algorithm is commonly used for training supervised learning models?

a)

K-means clustering

b)

Linear regression

c)

Random search

d)

Genetic algorithm

4.

What does the term "overfitting" refer to in AI model training?

a)

Model fits training data too closely

b)

Model ignores training data

c)

Model fits test data perfectly

d)

Model never learns

5.

Transfer learning involves:

a)

Training a model from scratch

b)

Using a pre-trained model for a new task

c)

Deleting all previous model weights

d)

Ignoring previous knowledge

6.

Which of the following is NOT a data collection method for AI models?

a)

Web scraping

b)

Surveys

c)

Data augmentation

d)

Sensor data

7.

Which technique is used to handle missing values in a dataset?

a)

Data duplication

b)

Data imputation

c)

Data hiding

d)

Data deletion

8.

Which algorithm is typically used for unsupervised learning?

a)

Decision tree

b)

K-means clustering

c)

Logistic regression

d)

Support vector machine

9.

Underfitting occurs when a model:

a)

Learns the training data too well

b)

Fails to capture the underlying pattern

c)

Has too many parameters

d)

Is trained for too long

10.

Which of the following is a benefit of transfer learning?

a)

Requires more data

b)

Reduces training time

c)

Increases model complexity

d)

Ignores previous knowledge

11.

If you have a dataset with both images and text, which data collection method would be most appropriate?

a)

Only web scraping

b)

Combining multiple sources

c)

Only surveys

d)

Only sensor data

12.

Why is normalization important in data preprocessing?

a)

It makes all data values zero

b)

It scales features to a similar range

c)

It removes all outliers

d)

It duplicates data

13.

How does gradient descent help in training AI models?

a)

By increasing the loss function

b)

By minimizing the loss function

c)

By deleting data points

d)

By randomizing model weights

14.

Which scenario is most likely to cause overfitting?

a)

Using a very simple model

b)

Training with too little data

c)

Training with too much data

d)

Using a very complex model

15.

How can transfer learning be applied to a new image classification task?

a)

Use a pre-trained model and fine-tune it on new images

b)

Train a new model from scratch

c)

Ignore all previous models

d)

Use only text data

16.

Which data collection method would you use to gather real-time weather data for an AI model?

a)

Surveys

b)

Sensor data

c)

Web scraping

d)

Data augmentation

17.

What is the effect of removing outliers during data preprocessing?

a)

Increases noise in the data

b)

Improves model accuracy

c)

Makes data less reliable

d)

Reduces data size only

18.

Which model training algorithm is best suited for classification tasks?

a)

Linear regression

b)

Logistic regression

c)

K-means clustering

d)

Principal component analysis

19.

How can you detect underfitting in a trained AI model?

a)

High accuracy on training data, low on test data

b)

Low accuracy on both training and test data

c)

High accuracy on test data only

d)

High accuracy on training data only

20.

Which step is essential when applying transfer learning to a new domain?

a)

Ignore the pre-trained model

b)

Fine-tune the pre-trained model on new data

c)

Use the pre-trained model without any changes

d)

Delete all previous weights

21.

You are tasked with building an AI model to predict house prices. How would you ensure the data collected is representative of the population?

a)

Collect data from only one neighborhood

b)

Collect data from diverse neighborhoods and house types

c)

Use only old data

d)

Ignore location information

22.

Given a dataset with missing values, which preprocessing strategy would you use to minimize bias in your AI model?

a)

Remove all rows with missing values

b)

Impute missing values using the mean or median

c)

Fill missing values with zeros

d)

Ignore missing values

23.

You are training a neural network and notice that the loss function is not decreasing. What could be a possible reason?

a)

Learning rate is too high or too low

b)

Model is overfitting

c)

Data is perfectly clean

d)

Model is too simple

24.

How would you address overfitting in a deep learning model?

a)

Add more layers to the model

b)

Use regularization techniques like dropout

c)

Reduce the amount of training data

d)

Increase the learning rate

25.

You want to use transfer learning for a medical image classification task. What is the best approach?

a)

Use a pre-trained model on natural images and fine-tune with medical images

b)

Train a model from scratch with medical images only

c)

Use a pre-trained model without any changes

d)

Use only text data

26.

If your AI model performs well on training data but poorly on test data, what does this indicate and how would you fix it?

a)

Overfitting; use techniques like cross-validation and regularization

b)

Underfitting; add more features

c)

Perfect model; do nothing

d)

Data is too clean; add noise

27.

You are given a large dataset with imbalanced classes. What preprocessing technique would you use to improve model performance?

a)

Ignore the imbalance

b)

Use resampling methods like oversampling or undersampling

c)

Remove the majority class

d)

Only use the minority class

28.

How would you select the best model training algorithm for a given task?

a)

Choose randomly

b)

Analyze the problem type and data characteristics

c)

Use the most popular algorithm

d)

Use the fastest algorithm

29.

You want to apply transfer learning to a text classification problem. What should you consider when choosing a pre-trained model?

a)

The pre-trained model should be trained on similar text data

b)

Any pre-trained model will work

c)

Use a model trained on images

d)

Ignore the domain of the pre-trained model

30.

Suppose your AI model is underfitting. What strategy would you use to improve its performance?

a)

Increase model complexity or add more features

b)

Reduce the amount of training data

c)

Use less data preprocessing

d)

Lower the learning rate

31.

What is the primary function of the Finch Robot?

a)

To play music

b)

To serve as an educational tool for learning programming and robotics

c)

To clean floors

d)

To cook food

32.

Which programming language is commonly used to program the Finch Robot?

a)

Python

b)

HTML

c)

CSS

d)

SQL

33.

Which sensor allows the Finch Robot to detect obstacles?

a)

Temperature sensor

b)

Light sensor

c)

Distance sensor

d)

Sound sensor

34.

What is one application of the Finch Robot in education?

a)

Teaching advanced calculus

b)

Demonstrating basic programming concepts

c)

Painting pictures

d)

Cooking recipes

35.

Which design principle is emphasized in the Finch Robot’s construction?

a)

Complexity

b)

Durability

c)

Simplicity and accessibility

d)

Luxury

36.

What is the main purpose of the Finch Robot’s LED lights?

a)

To provide entertainment

b)

To indicate status or feedback

c)

To heat the robot

d)

To power the robot

37.

Which sensor on the Finch Robot can measure ambient light?

a)

Temperature sensor

b)

Light sensor

c)

Distance sensor

d)

Pressure sensor

38.

What is the typical power source for the Finch Robot?

a)

Solar panels

b)

Batteries

c)

Gasoline

d)

Wind energy

39.

Which of the following is NOT a sensor found on the Finch Robot?

a)

Temperature sensor

b)

Light sensor

c)

Pressure sensor

d)

Distance sensor

40.

What is the main goal of programming the Finch Robot in a classroom setting?

a)

To win competitions

b)

To learn coding and robotics concepts

c)

To make phone calls

d)

To browse the internet

41.

If you want the Finch Robot to move forward for 2 seconds, which programming concept would you use?

a)

Loop

b)

Function call

c)

Variable assignment

d)

Conditional statement

42.

How can you use the Finch Robot’s sensors to avoid obstacles?

a)

By turning off the sensors

b)

By programming the robot to change direction when the distance sensor detects an object

c)

By ignoring sensor data

d)

By moving randomly

43.

Which programming structure would you use to make the Finch Robot repeat a movement pattern?

a)

If statement

b)

Loop

c)

Print statement

d)

Variable

44.

How can the Finch Robot’s LED lights be used in a classroom project?

a)

To display different colors based on sensor input

b)

To cook food

c)

To play music

d)

To print documents

45.

Which sensor would you use to program the Finch Robot to react to changes in room temperature?

a)

Light sensor

b)

Distance sensor

c)

Temperature sensor

d)

Sound sensor

46.

How can students use the Finch Robot to learn about algorithms?

a)

By memorizing robot parts

b)

By writing code that controls the robot’s movements and responses

c)

By drawing pictures of the robot

d)

By reading stories about robots

47.

If the Finch Robot’s light sensor detects a dark environment, what could you program it to do?

a)

Move backward

b)

Turn on its LED lights

c)

Play a sound

d)

Stop moving

48.

How does the Finch Robot’s design support collaborative learning?

a)

By being too complex for group work

b)

By allowing multiple students to program and test it together

c)

By limiting access to one user

d)

By not supporting programming

49.

Which sensor combination could be used to make the Finch Robot follow a line on the floor?

a)

Temperature and sound sensors

b)

Light and distance sensors

c)

Pressure and humidity sensors

d)

GPS and camera sensors

50.

How can the Finch Robot be used to demonstrate the concept of feedback in a system?

a)

By ignoring sensor data

b)

By using sensor input to adjust its actions, such as changing direction when an obstacle is detected

c)

By moving randomly

d)

By turning off all sensors

51.

A student wants the Finch Robot to avoid obstacles and reach a target location. What steps should they take to plan their program?

a)

Write random code and hope for the best

b)

Identify sensors needed, plan movement logic, and test the program iteratively

c)

Ignore sensor data and move straight

d)

Only use LED lights

52.

How can you use evidence from sensor readings to improve the Finch Robot’s performance in a maze?

a)

Ignore sensor readings

b)

Analyze sensor data to adjust movement and avoid walls more efficiently

c)

Only use pre-written code

d)

Move randomly

53.

A teacher wants students to use the Finch Robot to model a real-world system. Which approach demonstrates strategic thinking?

a)

Program the robot to move in a straight line

b)

Design a simulation where the robot mimics traffic flow using sensors and programmed rules

c)

Only use the robot’s LED lights

d)

Ignore sensor input

54.

How can students use the Finch Robot to investigate the relationship between light intensity and robot movement?

a)

Move the robot randomly

b)

Collect light sensor data and program the robot to change speed based on light levels, then analyze results

c)

Only use temperature sensor

d)

Ignore sensor data

55.

A group of students wants to design a classroom activity using the Finch Robot to teach about environmental monitoring. What should they consider in their planning?

a)

Only use the robot’s movement features

b)

Select relevant sensors, define data collection methods, and plan how to interpret results

c)

Ignore sensor capabilities

d)

Use the robot for entertainment only

56.

How can the Finch Robot’s design principles be applied to create a new educational robot?

a)

Make the robot as complex as possible

b)

Focus on simplicity, accessibility, and ease of programming for students

c)

Use expensive materials

d)

Ignore user needs

57.

A student observes that the Finch Robot is not responding to temperature changes. What reasoning process should they use to troubleshoot?

a)

Ignore the problem

b)

Check the temperature sensor, review the code, and test with different temperature sources

c)

Only change the batteries

d)

Move the robot to a different room

58.

How can the Finch Robot be used to demonstrate the concept of conditional logic in programming?

a)

By moving in a straight line regardless of input

b)

By using sensor data to make decisions, such as turning when an obstacle is detected

c)

By only using LED lights

d)

By ignoring all sensor input

59.

A teacher wants students to compare the effectiveness of different sensor combinations for a specific task. What should students do?

a)

Use only one sensor

b)

Test various sensor combinations, collect data, and analyze which combination works best for the task

c)

Ignore sensor data

d)

Only use pre-written code

60.

How can students use the Finch Robot to develop teamwork and problem-solving skills?

a)

Work individually without sharing ideas

b)

Collaborate to plan, program, and troubleshoot the robot’s tasks, reflecting on their strategies and outcomes

c)

Only use the robot for entertainment

d)

Ignore programming challenges

61.

Which of the following is a common method for collecting data to train AI models?

a)

Data mining

b)

Data painting

c)

Data erasing

d)

Data hiding

62.

What is the main purpose of data preprocessing in AI model training?

a)

To delete all data

b)

To clean and organize data

c)

To make data more confusing

d)

To hide data from the model

63.

Which algorithm is commonly used for training supervised learning models?

a)

K-means clustering

b)

Linear regression

c)

Random search

d)

Genetic algorithm

64.

What does the term "overfitting" refer to in AI model training?

a)

Model fits training data too closely

b)

Model ignores training data

c)

Model fits test data perfectly

d)

Model never learns

65.

Transfer learning involves:

a)

Training a model from scratch

b)

Using a pre-trained model for a new task

c)

Deleting all previous model weights

d)

Ignoring previous knowledge

66.

Which of the following is NOT a data collection method for AI models?

a)

Web scraping

b)

Surveys

c)

Data augmentation

d)

Sensor data

67.

Which technique is used to handle missing values in a dataset?

a)

Data duplication

b)

Data imputation

c)

Data hiding

d)

Data deletion

68.

Which algorithm is typically used for unsupervised learning?

a)

Decision tree

b)

K-means clustering

c)

Logistic regression

d)

Support vector machine

69.

Underfitting occurs when a model:

a)

Learns the training data too well

b)

Fails to capture the underlying pattern

c)

Has too many parameters

d)

Is trained for too long

70.

Which of the following is a benefit of transfer learning?

a)

Requires more data

b)

Reduces training time

c)

Increases model complexity

d)

Ignores previous knowledge

71.

If you have a dataset with both images and text, which data collection method would be most appropriate?

a)

Only web scraping

b)

Combining multiple sources

c)

Only surveys

d)

Only sensor data

72.

Why is normalization important in data preprocessing?

a)

It makes all data values zero

b)

It scales features to a similar range

c)

It removes all outliers

d)

It duplicates data

73.

How does gradient descent help in training AI models?

a)

By increasing the loss function

b)

By minimizing the loss function

c)

By deleting data points

d)

By randomizing model weights

74.

Which scenario is most likely to cause overfitting?

a)

Using a very simple model

b)

Training with too little data

c)

Training with too much data

d)

Using a very complex model

75.

How can transfer learning be applied to a new image classification task?

a)

Use a pre-trained model and fine-tune it on new images

b)

Train a new model from scratch

c)

Ignore all previous models

d)

Use only text data

76.

Which data collection method would you use to gather real-time weather data for an AI model?

a)

Surveys

b)

Sensor data

c)

Web scraping

d)

Data augmentation

77.

What is the effect of removing outliers during data preprocessing?

a)

Increases noise in the data

b)

Improves model accuracy

c)

Makes data less reliable

d)

Reduces data size only

78.

Which model training algorithm is best suited for classification tasks?

a)

Linear regression

b)

Logistic regression

c)

K-means clustering

d)

Principal component analysis

79.

How can you detect underfitting in a trained AI model?

a)

High accuracy on training data, low on test data

b)

Low accuracy on both training and test data

c)

High accuracy on test data only

d)

High accuracy on training data only

80.

Which step is essential when applying transfer learning to a new domain?

a)

Ignore the pre-trained model

b)

Fine-tune the pre-trained model on new data

c)

Use the pre-trained model without any changes

d)

Delete all previous weights

81.

You are tasked with building an AI model to predict house prices. How would you ensure the data collected is representative of the population?

a)

Collect data from only one neighborhood

b)

Collect data from diverse neighborhoods and house types

c)

Use only old data

d)

Ignore location information

82.

Given a dataset with missing values, which preprocessing strategy would you use to minimize bias in your AI model?

a)

Remove all rows with missing values

b)

Impute missing values using the mean or median

c)

Fill missing values with zeros

d)

Ignore missing values

83.

You are training a neural network and notice that the loss function is not decreasing. What could be a possible reason?

a)

Learning rate is too high or too low

b)

Model is overfitting

c)

Data is perfectly clean

d)

Model is too simple

84.

How would you address overfitting in a deep learning model?

a)

Add more layers to the model

b)

Use regularization techniques like dropout

c)

Reduce the amount of training data

d)

Increase the learning rate

85.

You want to use transfer learning for a medical image classification task. What is the best approach?

a)

Use a pre-trained model on natural images and fine-tune with medical images

b)

Train a model from scratch with medical images only

c)

Use a pre-trained model without any changes

d)

Use only text data

86.

If your AI model performs well on training data but poorly on test data, what does this indicate and how would you fix it?

a)

Overfitting; use techniques like cross-validation and regularization

b)

Underfitting; add more features

c)

Perfect model; do nothing

d)

Data is too clean; add noise

87.

You are given a large dataset with imbalanced classes. What preprocessing technique would you use to improve model performance?

a)

Ignore the imbalance

b)

Use resampling methods like oversampling or undersampling

c)

Remove the majority class

d)

Only use the minority class

88.

How would you select the best model training algorithm for a given task?

a)

Choose randomly

b)

Analyze the problem type and data characteristics

c)

Use the most popular algorithm

d)

Use the fastest algorithm

89.

You want to apply transfer learning to a text classification problem. What should you consider when choosing a pre-trained model?

a)

The pre-trained model should be trained on similar text data

b)

Any pre-trained model will work

c)

Use a model trained on images

d)

Ignore the domain of the pre-trained model

90.

Suppose your AI model is underfitting. What strategy would you use to improve its performance?

a)

Increase model complexity or add more features

b)

Reduce the amount of training data

c)

Use less data preprocessing

d)

Lower the learning rate