Your first ML project quiz

Question 1

What is the main idea of machine learning (ML)?

Accepted Answer

A computer learning patterns from examples to make predictions

Answer

A computer that never makes mistakes

Answer

A faster way to type code

Answer

A robot that looks like a human

Question 2

In an ML project, what do we usually call the examples the computer learns from?

Accepted Answer

Training data

Answer

The keyboard

Answer

The screen output

Answer

The power supply

Question 3

What is a 'feature' in a machine learning dataset?

Accepted Answer

An input property that describes an example

Answer

A bug in the program

Answer

The final answer the model gives

Answer

The name of the programmer

Question 4

What is a 'label' in supervised learning?

Accepted Answer

The correct answer attached to a training example

Answer

A sticker on the laptop

Answer

A random number

Answer

The file name of the code

Question 5

What is the difference between supervised and unsupervised learning?

Accepted Answer

Supervised uses labeled data; unsupervised finds patterns without labels

Answer

Supervised is always faster than unsupervised

Answer

Unsupervised needs more electricity

Answer

There is no real difference

Question 6

Why do we split data into a training set and a test set?

Accepted Answer

To check how well the model works on new, unseen data

Answer

To make the dataset smaller for fun

Answer

Because computers require exactly two files

Answer

To hide data from the user

Question 7

What does it mean when a model is 'overfitting'?

Accepted Answer

The model memorizes training data but fails on new data

Answer

The model is too small to run

Answer

The dataset has too few features

Answer

The computer overheats during training

Question 8

What is 'underfitting' in machine learning?

Accepted Answer

The model is too simple and performs poorly even on training data

Answer

The model is too accurate

Answer

There is too much training data

Answer

The screen is too small

Question 9

What is accuracy as a way to measure a classification model?

Accepted Answer

The fraction of predictions that are correct

Answer

The speed of the computer

Answer

The number of features used

Answer

The size of the code file

Question 10

What is the usual first step before training any ML model?

Accepted Answer

Collecting and preparing clean data

Answer

Buying a faster computer

Answer

Writing the final report

Answer

Deleting all the data

Question 11

What is a popular beginner Python library for machine learning?

Accepted Answer

scikit-learn

Answer

Microsoft Word

Answer

Photoshop

Answer

Notepad

Question 12

In scikit-learn, what does the .fit() method do?

Accepted Answer

It trains the model on the training data

Answer

It deletes the model

Answer

It prints the dataset

Answer

It downloads new data from the internet

Question 13

In scikit-learn, what does the .predict() method do?

Accepted Answer

It makes predictions for new input data

Answer

It trains the model from scratch

Answer

It charges the laptop battery

Answer

It changes the labels in the data

Question 14

What is the famous Iris flower dataset often used for in first ML projects?

Accepted Answer

Classifying iris flower species from measurements

Answer

Predicting tomorrow's weather

Answer

Translating languages

Answer

Playing chess

Question 15

What is the difference between classification and regression tasks?

Accepted Answer

Classification predicts categories; regression predicts numbers

Answer

Classification is for images only

Answer

Regression cannot use Python

Answer

They are exactly the same

Question 16

Which of these is a regression problem?

Accepted Answer

Predicting the price of a used bicycle

Answer

Deciding if a photo shows a cat or dog

Answer

Sorting emails into spam or not spam

Answer

Identifying the language of a sentence

Question 17

What is a 'model' in machine learning?

Accepted Answer

The learned patterns that turn inputs into predictions

Answer

A fashion mannequin

Answer

The computer's hard drive

Answer

A type of keyboard

Question 18

Why is it important to have enough good-quality data for an ML project?

Accepted Answer

More good data helps the model learn real patterns

Answer

Data is only for decoration

Answer

Less data always works better

Answer

Data has no effect on the model

Question 19

What is a decision tree in simple terms?

Accepted Answer

A model that asks yes/no questions like a flowchart

Answer

A real tree planted in a garden

Answer

A type of computer monitor

Answer

A way to store passwords

Question 20

What does 'generalization' mean for a machine learning model?

Accepted Answer

Performing well on new, unseen data

Answer

Memorizing the training data exactly

Answer

Running the code faster

Answer

Using less memory

Question 21

What is data cleaning, and why is it needed in an ML project?

Accepted Answer

Fixing errors and missing values so the model learns well

Answer

Wiping the computer screen

Answer

Deleting the whole project

Answer

Changing the desktop wallpaper

Question 22

What is a 'prediction' in machine learning?

Accepted Answer

The model's output guess for a new input

Answer

The training data itself

Answer

An error message

Answer

The name of the algorithm

Question 23

Why might a model trained only on data from one city perform poorly in another city?

Accepted Answer

Its training data did not represent the new city

Answer

Computers cannot work in new cities

Answer

Predictions always fail after one week

Answer

The model forgets data over distance

Question 24

What is bias in a machine learning dataset?

Accepted Answer

Data that unfairly favors or ignores certain groups

Answer

A type of fast computer chip

Answer

A Python keyword

Answer

A way to speed up training

Question 25

Why is privacy an important ethical concern in ML projects?

Accepted Answer

Personal data must be used responsibly and with permission

Answer

Privacy makes models run faster

Answer

Privacy only matters for video games

Answer

Privacy is not related to data

Question 26

What is the role of the 'target' (y) variable in a supervised ML project?

Accepted Answer

The value the model is trained to predict

Answer

A decoration in the chart

Answer

The speed of training

Answer

The number of rows in the data

Question 27

What does normalizing or scaling features mean, and why can it help?

Accepted Answer

Putting features on a similar range so none dominates unfairly

Answer

Deleting all large numbers

Answer

Making the screen brighter

Answer

Renaming the columns

Question 28

If a spam filter wrongly marks an important email as spam, what type of mistake is that?

Accepted Answer

A false positive

Answer

A true positive

Answer

A perfect prediction

Answer

A training error

Question 29

Why should you not test a model on the same data you trained it on?

Accepted Answer

It can give a falsely high score and hide overfitting

Answer

It uses too much electricity

Answer

It is against Python rules

Answer

It makes the model smaller

Question 30

What is a simple way to describe how a model 'learns' during training?

Accepted Answer

It adjusts itself to reduce its mistakes over many examples

Answer

It copies answers from the internet

Answer

It guesses once and stops

Answer

It memorizes the programmer's name

Test yourself