wayground logo

Free Printable Worksheets

NEW

Font size

S
M
L
XL
Worksheets

Midterm_Quiz2_M7-8

Total questions: 20

Worksheet time: 10mins

Name
Class
Date
1.

What is the main goal of feature selection?

a)

 Increase data redundancy

b)

 Remove irrelevant and redundant features

c)

Add more variables

d)

 Ignore model performance

2.

Which problem often occurs when a dataset has too many features?

a)

Underfitting

b)

Missing values

c)

Overfitting

d)

Bias

3.

PCA stands for:

a)

Principal Classification Analysis

b)

Principal Component Analysis

c)

Primary Component Algorithm

d)

Projection Coefficient Analysis

4.

Which of the following is a filter method?

a)

Correlation Coefficient Analysis

b)

Recursive Feature Elimination

c)

Decision Tree Importance

d)

Lasso Regression

5.

Which feature selection method evaluates subsets of features by testing model performance?

a)

 Filter

b)

Wrapper

c)

Embedded

d)

Regularization

6.

What type of dimensionality reduction is PCA?

a)

Linear

b)

Nonlinear

c)

Hierarchical

d)

Randomized

7.

In PCA, new variables formed after transformation are called:

a)

Eigenvectors

b)

Principal Components

c)

Latent Variables

d)

Hidden Layers

8.

The first principal component represents the:

a)

Highest variance in data

b)

Smallest variance

c)

Noise in data

d)

Average of features

9.

Which method is most used for visualizing clusters in high-dimensional data?

a)

 PCA

b)

t-SNE

c)

LDA

d)

Random Forest

10.

What is the benefit of dimensionality reduction?

a)

It increases processing time

b)

It simplifies the dataset without losing much information

c)

It makes models more complex

d)

It removes outliers

11.

Overfitting occurs when a model __________.

a)

Ignores important features

b)

Learns the noise in the training data

c)

Has too few parameters

d)

Has perfect test accuracy

12.

Underfitting happens when a model __________.

a)

Memorizes data patterns

b)

Is too simple to capture data patterns

c)

Overlearns the noise

d)

Has too many layers

13.

A model that performs well on training data but poorly on test data is likely __________.

a)

Underfitted

b)

Overfitted

c)

 Regularized

d)

Balanced

14.

Which of the following best describes underfitting?

a)

 The model performs poorly on both training and test data

b)

The model performs perfectly on training data

c)

The model learns the noise

d)

The model is highly complex

15.

What is the main cause of overfitting?

a)

Too little data

b)

Excessive model complexity

c)

Poor feature scaling

d)

Low regularization

16.

What is the main cause of underfitting?

a)

Too much regularization

b)

Too simple model or missing important features

c)

Overtraining

d)

Data duplication

17.

Which method adds penalties to control model complexity?

a)

Regularization

b)

Clustering

c)

Normalization

d)

Feature scaling

18.

L1 regularization (Lasso) tends to __________.

a)

Keep all coefficients equal

b)

Remove unnecessary features

c)

Increase coefficients

d)

Add random noise

19.

L2 regularization (Ridge) tends to __________.

a)

 Remove features completely

b)

Ignore small features

c)

Reduce coefficients without removing them

d)

Overfit the data

20.

Cross-validation helps by __________.

a)

Adding more features

b)

 Increasing dataset size

c)

Reducing noise manually

d)

Testing model performance on different data subsets