wayground logo

Free Printable Worksheets

Font size

S
M
L
XL
Worksheets

Quiz on machine learning

Total questions: 20

Worksheet time: 10mins

Name
Class
Date
1.

In a classification problem, the outputs are

a)

categorical or discrete

b)

numerical or continuous

2.

In a regression problem, the output is _

a)

categorical or discrete

b)

numerical or continuous

3.

What is the difference between K-means and KNN Algorithms?

a)

K-means is supervised while KNN is unsupervised

b)

K-Means is used for clustering while KNN is used for classification and regression

4.

KNeighborsClassifier class can be imported as:

a)

from sklearn.ensemble import KNeighborsClassifier

b)

from sklearn.neighbors import KNeighborsClassifier

c)

from sklearn.tree import KNeighborsClassifier

d)

from sklearn import KNeighborsClassifier

5.

Which of the following is FALSE about SVM?

a)

SVM has inbuilt L2 regularization capabilities

b)

SVM solves both classification and regression problems

c)

It does not require any feature scaling

d)

Choosing an appropriate Kernel function is difficult

6.

Which of the following is FALSE about Entropy in context of Decision Tree?

a)

Entropy keeps on increasing as we keep splitting the nodes

b)

Entropy is calculated using Information Gain

c)

None of the above

7.

Which of the following is FALSE about Random Forest and Adaboost?

a)

Random Forest aims to decrease variance and not bias

b)

Adaboost aims to decrease bias not variance

c)

Both Adaboost and Random Forest aim to decrease both bias and variance

d)

None of the above

8.

Which of the following is TRUE about Random Forest and Adaboost?

a)

Order of trees matters in Random Forest

b)

Order of trees matters in Adaboost

c)

Order of trees does not matter in Random Forest and Adaboost

d)

None of the above

9.

Which of the following is FALSE about Boosting?

a)

Each weak learner has equal say in the final decision

b)

Sequence in which each weak learner is created does not matter

c)

None of the above

10.

Which of the following is TRUE about Reinforcement Learning?

a)

It uses rewards and penalty methods to train a model

b)

It is also known as a semi - supervised learning model

c)

Chess playing computer is a good example of reinforcement learning

d)

All of the above

11.

Which of the following algorithm is called Lazy Learner?

a)

KNN

b)

SVM

c)

Naive Bayes

d)

Decision Tree

12.

Which of the following is NOT an example of hyper-parameter?

a)

Number of nearest neighbors in KNN

b)

Number of outliers in KNN

c)

Depth of a Decision Tree

d)

Number of trees in a Random Forest

13.

Which of the following is FALSE about Tuples in Python?

a)

Tuples are immutable

b)

Tuple items can be deleted using del keyword

c)

Tuples can be declared as: x,y=1,2

d)

None of the above

14.

Which of the following is TRUE about Random Forest?

a)

Random Forest aims to decrease both variance and bias

b)

Random Forest aims to decrease variance not bias

c)

Random Forest aims to decrease bias not variance

d)

None of the above

15.

Dimensionality Reductions is useful because it:

a)

reduces overfitting

b)

reduces computation time

c)

removes multicollinearity

d)

All of the above

16.

What do minimum missing value ratio represent?

a)

The number of missing values in a dataset

b)

The number of minimum missing values for an operation to be performed

c)

The number of missing values in a column

d)

The minimum ratio of missing values to all values in a column for cleaning to be performed

17.

Which of these are not displayed when you see the import data result visualization?

a)

Unique values

b)

Missing values

c)

Standard deviation

d)

Mode

18.

Compute target is the target variable whose value is to predicted.

a)

True

b)

False

19.

'Convert to CSV' module is a part of which section?

a)

Data Input and Output

b)

Data Transformation

c)

Model Training

d)

None of the above

20.

The key challenge to successfully train a machine learning model

a)

Feature engineering and selection

b)

Selection of the algorithm

c)

Tuning of the hyperparameters

d)

Evaluation of the metrics

e)

All the above