wayground logo

Free Printable Worksheets

Font size

S
M
L
XL
Worksheets

ML-MIDTERM-20251

Total questions: 60

Worksheet time: 10mins

Name
Class
Date
1.

What is artificial intelligence primarily defined as?

a)

The development of computer hardware

b)

The simulation of human intelligence by machines

c)

The creation of robots only

d)

The process of data collection

2.

What is Predictive Analytics primarily used for?

a)

Describing historical data

b)

Forecasting future outcomes using data

c)

Cleaning data for analysis

d)

Encrypting sensitive data

3.

Which of the following is considered a feature in a dataset?

a)

Purchased: Yes/No

b)

Age, income, credit score

c)

Model prediction

d)

Evaluation metric

4.

What does the label in a dataset represent?

a)

Independent variable

b)

Algorithm used

c)

Dependent variable or output

d)

Training process

5.

Which of these is NOT a core component of AI?

a)

Computer vision

b)

Natural language processing

c)

Database management

d)

Speech recognition

6.

What is machine learning?

a)

A type of computer programming

b)

A method of hardware optimization

c. A branch of AI focusing on data and algorithms to imitate human learning
d. The process of building physical robots

c)

A branch of AI focusing on data and algorithms to imitate human learning

d)

The process of building physical robots

7.

In supervised learning, what is essential?

a)

Unlabeled datasets

b)

Random data collection

c)

No human intervention

d)

Labeled datasets

8.

What is the primary function of collaborative filtering?

a)

To block unwanted content

b)


To organize data alphabetically

c)

To filter items based on similar users' reactions

d)

To speed up computer processing

9.

What is a key characteristic of unsupervised learning?

a)

It requires labeled datasets

b)

It needs constant human supervision

c)

It discovers hidden patterns without human intervention

d)

It only works with numerical data

10.

What is Naive Bayes' key assumption?

a)

All predictors are dependent

b)

All predictors are independent

c)

Only numerical data can be used

d)

It requires human supervision

11.

What percentage of data is typically used for training in the machine learning model discussed?

a)

90%

b)

70%

c)

60%

d)

80%

12.

What is overfitting in machine learning?

a)

When the model is too simple

b)

When the model covers more than required data points

c)

When the model has no variance

d)

When the model is undertrained

13.

What is a confusion matrix used for?

a)

To confuse the machine learning model

b)

To organize raw data

c)

To define classification algorithm performance

d)

To create neural networks

14.

What does a True Positive (TP) in a confusion matrix indicate?

a)

An incorrect negative prediction

b)

An incorrect positive prediction

c)

A correct positive prediction

d)

A missed prediction

15.

What is precision in machine learning metrics?

a)

The speed of processing

b)

The ratio of correct positive predictions to total positive predictions

c)

The total accuracy score
d. The model's processing power

d)

The model's processing power

16.

What is predictive analytics?

a)

Looking at past data only

b)

Organizing current data

c)

Using data to forecast future outcomes

d)

Analyzing hardware performance

17.

Which is NOT a way to avoid overfitting?

a)

Cross-validation

b)

Reducing training data

c)

Early stopping

d)

Regularization

18.

What is underfitting characterized by?

a)

High variance and low bias

b)

Low variance and low bias

c)

High bias and low variance

d)

Perfect predictions

19.

What is the command for showing the fist five record using pandas?

a)

head()

b)

tail()

c)

select ()

d)

range(5)

20.

Which metric measures the proportion of actual positives correctly identified?

a)

Recall

b)

Specificity

c)

c. Accuracy

d)

Precision

21.

What is content-based filtering primarily based on?

a)

User demographics

b)

Historical data only

c)

Item features and user preferences

d)

Random selection

22.

What tool provides machine learning algorithms for classification and regression?

a)
Pandas
b)
Keras
c)
Scikit-learn
d)
TensorFlow
23.

What is the primary purpose of cross-validation?

a)

To increase processing speed

b)

To ensure model reliability

c)

To reduce data size

d)

To create new data

24.

Which type of learning does not require labeled data?

a)

Supervised learning

b)

Semi-supervised learning

c)

Unsupervised learning

d)

Reinforced learning

25.

What is the primary challenge with text data from the internet?

a)

It's mostly unlabeled

b)

It's too structured

c)

It's not accessible

d)

It's too small

26.

Which of the following is a supervised learning task?

a)

Image compression

b)

Customer segmentation

c)

Spam email classification

d)

Topic modeling

27.

Which of these is an example of regression?

a)

Fraud detection

b)

Loan approval

c)

Stock price prediction

d)

Face recognition

28.

What type of data does unsupervised learning use?

a)

Labeled data

b)

Unlabeled data

c)

Both labeled and unlabeled data

d)

None

29.

Which algorithm is commonly used for clustering?

a)

Decision Tree

b)

Random Forest

c)

K-Means

d)

Naïve Bayes

30.

Which type of learning involves reward and punishment to improve performance?

a)

Supervised Learning

b)

Unsupervised Learning

c)

Reinforcement Learning

d)

Deep Learning

31.

What is the main goal of data preprocessing?

a)

Collecting more data

b)

Cleaning and transforming data

c)

Building neural networks

d)

Creating test data

32.

In supervised learning, labels refer to:

a)

Input variables

b)

Independent variables

c)

Target variables

d)

Features

33.

Which of the following is structured data?

a)

Tweets

b)

Images

c)

Tables in a database

d)

Audio recordings

34.

Which of the following is unstructured data?

a)

Gender column in Excel

b)

Student grades table

c)

Product reviews

d)

Salary records

35.

What is the purpose of training data?

a)

To test model accuracy

b)

To evaluate model performance

c)

To help the model learn patterns

d)

To clean data

36.

Testing data is used to:

a)

Train the model

b)

Evaluate model generalization

c)

Store old datasets

d)

Build new models

37.

Which of the following can cause underfitting?

a)

Too complex model

b)

Too simple model

c)

Large dataset

d)

Deep neural network

38.

Which of the following is a symptom of overfitting?

a)

High bias, low variance

b)

High training accuracy, low test accuracy

c)

Low training accuracy

d)

Small dataset with poor results

39.

Bias occurs when a model is ______.

a)

Too simple

b)

Too complex

c)

Too accurate

d)

Too large

40.

Variance occurs when a model is ______.

a)

Too simple

b)

Too complex

c)

Too accurate

d)

Too large

41.

The bias-variance tradeoff seeks to balance:

a)

Data quality and data size

b)

Simplicity and complexity

c)

Accuracy and speed

d)

Precision and recall

42.

In classification, which metric measures the proportion of correctly predicted positive observations?

a)

Precision

b)

Recall

c)

F1-score

d)

Accuracy

43.

Which step is NOT part of using Google’s Teachable Machine?

a)

Collect and label images

b)

Train the model

c)

Write code manually

d)

Test the model

44.

Machine Learning differs from traditional programming because it:

a)

Uses rules explicitly written by humans

b)

Learns automatically from data

c)

Doesn’t require data

d)

Focuses only on robotics

45.

Unstructured data includes which of the following?

a)

Tables

b)

Database records

c)

Text, image, audio, and video data

d)

Numerical data

46.

What is the purpose of data preprocessing?

a)

To create training models

b)

To clean and organize raw data for analysis

c)

To visualize the dataset

d)

To store large amounts of data

47.

What does data cleaning involve?

a)

Formatting reports

b)

Fixing or removing incorrect or duplicate data

c)

Creating dashboards

d)

Gathering new data

48.

What is the training dataset used for?

a)

Testing model accuracy

b)

Visualizing patterns

c)

Teaching the model to learn from data

d)

Evaluating performance

49.

What is the purpose of the testing dataset?

a)

To build the model

b)

To train the model

c)

To evaluate model performance on unseen data

d)

To clean the data

50.

Underfitting happens when a model:

a)

Memorizes the training data

b)

Fails to capture underlying patterns in the data

c)

Overlearns the noise in data

d)

Uses too many features

51.

Bias in machine learning refers to:

a)

The model learning too much from noise

b)

Error from overly simple assumptions

c)

Large variability in predictions

d)

Overtraining the model

52.

Variance in machine learning refers to:

a)

Model’s simplicity

b)

Learning too little

c)

Model learning too much from data noise

d)

Missing values in data

53.

Naive Bayes classifier assumes:

a)

All features are dependent

b)

Features are independent of each other

c)

Data must be normalized

d)

The model uses clustering methods

54.

What is the function of model.predict() in Scikit-learn?

a)

Train a model

b)

Split data into sets

c)

Predict labels for new data

d)

Calculate accuracy

55.

What does True Positive (TP) represent?

a)

Predicted negative, actual positive

b)

Predicted positive, actual positive

c)

Predicted positive, actual negative

d)

Predicted negative, actual negative

56.

Accuracy is calculated using which formula?

a)

(TP + FP) / Total

b)

(TP + TN) / Total

c)

(TP + FN) / Total

d)

(FP + TN) / Total

57.

Which performance metric measures how many of the predicted positives are actually positive?

a)

Recall

b)

Precision

c)

F1-Score

d)

Accuracy

58.

The F1-Score combines which two metrics?

a)

Accuracy and Recall

b)

Precision and Recall

c)

True Positive and False Positive

d)

Sensitivity and Specificity

59.

What is the formula for Precision?

a)

TP ÷ (TP + FP)

b)

TP ÷ (TP + FN)

c)

TN ÷ (TN + FP)

d)

FN ÷ (FP + TN)

60.

What is the formula for Recall?

a)

TP ÷ (TP + FP)

b)

TP ÷ (TP + FN)

c)

TN ÷ (TN + FP)

d)

FP ÷ (FP + TN)