wayground logo

Free Printable Worksheets

Font size

S
M
L
XL
Worksheets

Machine Learning Quiz

Total questions: 86

Worksheet time: 43mins

Name
Class
Date
1.

Machine Learning mainly focuses on:

a)

Writing manual rules

b)

Learning patterns from data

c)

Only storing data

d)

Only cleaning data

2.

Which of the following is NOT a type of Machine Learning?

a)

Supervised

b)

Unsupervised

c)

Reinforcement

d)

Typographic learning

3.

In supervised learning, the model learns using:

a)

Only unlabeled data

b)

Labeled data

c)

No data

d)

Random data

4.

Unsupervised learning works with:

a)

Labeled data

b)

Unlabeled data

c)

Data with missing values

d)

Only image data

5.

Which of the following is an example of ML application?

a)

Fans

b)

Automatic email spam detection

c)

Ceiling lights

d)

None

6.

Data preprocessing means:

a)

Buying new data

b)

Cleaning and preparing data

c)

Ignoring data

d)

Deleting all missing values

7.

EDA stands for:

a)

Easy Data Analysis

b)

Exploratory Data Analysis

c)

Extra Data Adjustment

d)

Enhanced Data Algorithm

8.

Which is NOT an ML application?

a)

Weather prediction

b)

Face recognition

c)

Text translation

d)

Manual typewriter

9.

Semi-supervised learning uses:

a)

Only labeled data

b)

Both labeled and unlabeled data

c)

No data

d)

Only video data

10.

Reinforcement Learning is based on:

a)

Rewards and penalties

b)

Labeled data

c)

Image processing

d)

Text analysis

11.

Which comes first in ML workflow?

a)

Model training

b)

Data preprocessing

c)

Model deployment

d)

Model evaluation

12.

A dataset is:

a)

A single number

b)

A collection of data

c)

A machine

d)

A graph

13.

Missing values in data should be:

a)

Ignored

b)

Handled properly

c)

Always deleted

d)

Increased

14.

Which term refers to understanding data using graphs?

a)

Deployment

b)

Prediction

c)

Exploratory analysis

d)

Modeling

15.

Which is a supervised learning task?

a)

K-Means

b)

PCA

c)

Regression

d)

t-SNE

16.

ML is a part of:

a)

Chemistry

b)

Artificial Intelligence

c)

Geography

d)

History

17.

The target variable exists in:

a)

Unsupervised learning

b)

Supervised learning

c)

Always

d)

Never

18.

ML models learn through:

a)

Patterns

b)

Fixed rules

c)

Random selection

d)

Guess

19.

Label means:

a)

A type of image

b)

Correct output

c)

A file name

d)

Dataset size

20.

ML helps in:

a)

Automating decisions

b)

Cooking food

c)

Painting walls

d)

None

21.

Linear Regression predicts:

a)

Categories

b)

Continuous values

c)

Words

d)

Images

22.

Logistic Regression is used for:

a)

Regression only

b)

Classification

c)

Dimensionality reduction

d)

Clustering

23.

Decision Trees are used for:

a)

Only regression

b)

Only classification

c)

Both classification and regression

d)

Only clustering

24.

Random Forest is a type of:

a)

Single model

b)

Ensemble model

c)

Deep learning model

d)

Reinforcement model

25.

KNN depends on:

a)

Distance

b)

Trees

c)

Layers

d)

Rewards

26.

SVM stands for:

a)

Support Vector Machine

b)

System Vector Mode

c)

Simple Variable Machine

d)

Standard Value Measure

27.

Which algorithm uses Bayes’ theorem?

a)

Random Forest

b)

Naïve Bayes

c)

K-Means

d)

PCA

28.

Gradient Descent is used for:

a)

Minimizing error

b)

Increasing error

c)

Sorting data

d)

Clustering

29.

Boosting improves model performance by:

a)

Reducing data

b)

Combining weak learners

c)

Increasing noise

d)

Ignoring errors

30.

AdaBoost stands for:

a)

Adaptive Boosting

b)

Added Boosting

c)

Advanced Boosting

d)

Auto Boosting

31.

XGBoost is widely used because it is:

a)

Slow

b)

Very fast and accurate

c)

Only for images

d)

Very old

32.

Accuracy measures:

a)

Correct predictions

b)

Model speed

c)

Training time

d)

Dataset size

33.

Precision measures:

a)

Correct positive predictions

b)

Total data quality

c)

Feature size

d)

Negative classes

34.

Recall measures:

a)

All predicted positives

b)

Correctly identified actual positives

c)

False negatives

d)

Dataset noise

35.

F1 score is:

a)

Average of precision & recall

b)

Sum of precision & recall

c)

Accuracy

d)

Loss

36.

ROC curve is used to evaluate:

a)

Clustering

b)

Classification models

c)

Regression

d)

PCA

37.

Cross-validation helps to:

a)

Reduce overfitting

b)

Increase dataset

c)

Change model type

d)

Delete labels

38.

Feature means:

a)

Row

b)

Column

c)

Label

d)

File

39.

Training data is used to:

a)

Evaluate model

b)

Deploy model

c)

Teach the model

d)

Ignore errors

40.

Test data is used to:

a)

Train the model

b)

Check model performance

c)

Remove data

d)

Normalize data

41.

K-Means is a:

a)

Supervised algorithm

b)

Unsupervised algorithm

c)

NLP algorithm

d)

Deep learning model

42.

Clustering means:

a)

Grouping similar data

b)

Predicting numbers

c)

Translating text

d)

Measuring accuracy

43.

DBSCAN identifies clusters based on:

a)

Distance & density

b)

Labels

c)

Features

d)

Weights

44.

DBSCAN identifies clusters based on:

a)

Distance & density

b)

Labels

c)

Features

d)

Weights

45.

Hierarchical clustering produces:

a)

A tree-like structure

b)

A single number

c)

A deep network

d)

A regression line

46.

Dimensionality reduction reduces:

a)

Rows

b)

Columns/features

c)

Labels

d)

Accuracy

47.

PCA stands for:

a)

Principal Component Analysis

b)

Primary Component Arrangement

c)

Partial Clustering Algorithm

d)

Principal Category Analysis

48.

PCA is mainly used for:

a)

Clustering

b)

Reducing features

c)

Regression

d)

Classification

49.

LDA stands for:

a)

Linear Data Algorithm

b)

Linear Discriminant Analysis

c)

Learning Data Arrangement

d)

Label Distribution Analysis

50.

t-SNE is used for:

a)

Visualization

b)

Regression

c)

Boosting

d)

Data cleaning

51.

Unsupervised learning does NOT require:

a)

Labels

b)

Data

c)

Features

d)

Algorithm

52.

The number of clusters in K-Means is:

a)

Decided automatically

b)

Given by the user

c)

Always 2

d)

Always 5

53.

Outliers are handled well by:

a)

K-Means

b)

DBSCAN

c)

SVM

d)

Linear Regression

54.

Similar data means:

a)

Identical labels

b)

Similar patterns

c)

Same images

d)

Same size

55.

High-dimensional data means:

a)

Many features

b)

Many labels

c)

Many rows

d)

Noisy data

56.

Semi-supervised learning requires:

a)

100% labeled data

b)

Few labeled + many unlabeled data

c)

No data

d)

Only images

57.

Reinforcement Learning belongs to:

a)

Unsupervised learning

b)

Trial-and-error learning

c)

Data mining

d)

NLP

58.

In clustering, groups are called:

a)

Trees

b)

Clusters

c)

Labels

d)

Predictions

59.

PCA components are:

a)

New transformed features

b)

Labels

c)

Predictions

d)

Classes

60.

Hierarchical clustering uses:

a)

Dendrogram

b)

Histogram

c)

ROC curve

d)

Precision curve

61.

Unsupervised learning helps in:

a)

Grouping

b)

Labeling

c)

Predicting exact value

d)

Testing

62.

Deep learning models are inspired by:

a)

Human brain

b)

Trees

c)

Cars

d)

Gravity

63.

CNNs are best for:

a)

Images

b)

Audio

c)

Text

d)

Tables

64.

RNNs are best for:

a)

Independent data

b)

Sequence data

c)

Random data

d)

Geographical data

65.

NLP deals with:

a)

Robots

b)

Numbers

c)

Human language

d)

Weather

66.

Text preprocessing includes:

a)

Cleaning text

b)

Writing text

c)

Printing text

d)

Encrypting text

67.

Word embeddings represent words as:

a)

Images

b)

Vectors

c)

Tables

d)

Files

68.

Transformer models work using:

a)

Attention mechanism

b)

Convolution

c)

Reward system

d)

Decision trees

69.

BERT is used for:

a)

Translation

b)

Text understanding

c)

Image processing

d)

Sound detection

70.

GPT stands for:

a)

Generative Pre-trained Transformer

b)

General Processing Technique

c)

Graphical Pattern Tool

d)

General Prediction Transformer

71.

Deep learning requires:

a)

More data

b)

Less data

c)

No data

d)

Only labels

72.

CNN stands for:

a)

Convolutional Neural Network

b)

Convolution Neural Node

c)

Component Neural Net

d)

Classified Neural Network

73.

RNN stands for:

a)

Recurrent Neural Network

b)

Recursive Neural Node

c)

Regional Neural Net

d)

Random Neural Network

74.

Transfer Learning helps by:

a)

Starting from scratch

b)

Using pre-trained models

c)

Ignoring learning

d)

Training endlessly

75.

NLP is used in:

a)

Chatbots

b)

Washing machines

c)

Refrigerators

d)

Lights

76.

Tokens in NLP are:

a)

Sentences

b)

Words or subwords

c)

Tables

d)

Features

77.

Stop words are:

a)

Important words

b)

Common words to remove

c)

Numbers

d)

Special features

78.

Word2Vec is used for:

a)

Clustering

b)

Creating word vectors

c)

Cleaning text

d)

Filtering labels

79.

Sentiment analysis checks:

a)

Grammar

b)

Emotions in text

c)

Model speed

d)

Image size

80.

Padding in DL is used to:

a)

Match sequence lengths

b)

Remove noise

c)

Increase accuracy

d)

Reduce time

81.

NLP models convert text into:

a)

Sound

b)

Numbers

c)

Images

d)

Labels

82.

Time series data is collected:

a)

Randomly

b)

Over time intervals

c)

Without order

d)

Only once

83.

A popular time-series plot is:

a)

Bar chart

b)

Line chart

c)

Pie chart

d)

Scatter

84.

Forecasting means:

a)

Checking past

b)

Predicting future

c)

Deleting data

d)

Visualizing

85.

LSTM stands for:

a)

Long Short-Term Memory

b)

Large Short-Term Machine

c)

Long Supervised Time Model

d)

Linear System Time Model

86.

LSTM is used for:

a)

Sequence prediction

b)

Static data

c)

Clustering

d)

Visualization