wayground logo

Free Printable Worksheets

Font size

S
M
L
XL
Worksheets

Nurkhat

Total questions: 70

Worksheet time: 36mins

Name
Class
Date
1.

Lasso can be interpreted as least-squares linear regression where 

a)

weights are regularized with the L1 norm

b)

the weights have a Gaussian prior

c)

weights are regularized with the L2 norm

d)

the solution algorithm is simpler e. None of the above

2.

What is overfitting? 

a)

Great result in training and poor result in test

b)

Great result in training and great result in test

c)

Poor result in training and poor result in test

3.

 ... shows how far is a ?average model? from the ground truth 

a)

Bias

b)

MSE

c)

Variance

d)

R squared

4.

Which of the following techniques can be used for keyword normalization in NLP, the process of converting a keyword into its base form?

a)

Lemmatization

b)

Soundex

c)

Cosine Similarity

d)

N-grams

5.

Which of the following indicates a fairly strong relationship between X and Y?

a)

Correlation coefficient = 0.9

b)

The p-value for the null hypothesis Beta coefficient =0 is 0.0001

c)

The t-statistic for the null hypothesis Beta coefficient =0 is 30

d)

None of the above

6.

You trained a binary classifier model which gives very high accuracy on the training data, but much lower accuracy on validation data. The following may be true:

a)

This is an instance of overfitting

b)

This is an instance of underfitting.

c)

The training was not well regularized.

d)

The training and testing examples are sampled from different distributions

7.

Which way Lasso Regression differs from Ridge Regression? 

a)

It uses absolute values in regularization parameter, instead of squares

b)

It uses square values in regularization parameter

c)

It works better in small datasets

d)

It works better in big datasets

None of the above

8.

What kind of function is used to predict in the sklearn library? 

a)

predict()

b)

test()

c)

find()

d)

None of the above

9.

Which is not a sample of classification problem?

a)

To predict the amount of money a customer will spend in one year

b)

To predict whether a customer switches to another provider or brand

c)

To predict the category to which customer belongs to

d)

To predict whether a customer responds to a particular advertising campaign or not

10.

Regarding bias and variance, which of the following statements are true? (select multiple)

a)

Models which overfit have a high bias.

b)

Models which overfit have a low bias.

c)

Models which underfit have a low variance.

d)

None of the above

11.

 In a simple linear regression model (One independent variable), If we change the input variable by 1 unit. How much will the output variable change?

a)

By 1


b)

By change

c)

By its Slope

d)

No change

12.

. ... in classification problems is the number of correct predictions made by the model over all kinds of predictions made.

a)

Accuracy

b)

F1 Score

c)

Recall

d)

Precision

13.

To test the linear relationship of y(dependent) and x(independent) continuous variables, which of the following plots is best suited?

a)

Scatter plot

b)

Barchart

c)

Histograms

d)

All of the above

14.

What is the true positive? 

a)

Ground truth: True, Predicted: True

b)

Ground truth: False, Predicted: False

c)

Ground truth: True, Predicted: False

d)

Ground truth: False, Predicted: True

15.

Which of the following methods) does not have a closed form solution for its coefficients?

a)

Ridge regression

b)

Lasso

c)

None of both

d)

Clear selection

16.

What is overfitting?

a)

Great result in training and poor result in test

b)

Great result in training and great result in test

c)

Poor result in training and poor result in test

d)

Poor result in training and poor result in test

17.

Which of the following is true about "Ridge" or "Lasso" regression methods in case of feature selection?

a)

Lasso regression uses subset selection of features

b)

Ridge regression uses subset selection of features

c)

Both use subser selection of features

d)

None of above All of the above

18.

Natural Language processing can be used in

a)

Text classification


b)

All of the above

c)

Chatbots

d)

Topic modeling

19.

The correlation coefficient is used to determine:

a)

The strength of the relationship between the x and y variables

b)

A specific value of the y-variable given a specific value of the x-variable

c)

A specific value of the x-variable given a specific value of the y-variable

d)

All of the above

20.

You are predicting whether an email is spam or not. Based on the features, you obtained an estimated probability to be 0.75. What's the meaning of this estimated probability?

(select two)

a)

there is 75% chance that the email will be spam

b)

there is 25% chance that the email will be spam

c)

there is 75% chance that the email will not be spam

d)

there is 25% chance that the email will not be spam

21.

The response variable can belong to one of three or more categories and there is a natural ordering among the categories.

a)

Binary logistic regression

b)

Ordinal logistic regression

c)

Multinomial logistic regression

d)

Linear regression

22.

Overfitting is ...

a)

a good performance on training data and poor performance on unseen data

b)

the idea that simpler models should be used more frequently than complex

c)

a strategy to make complex models (like the decision tree) more robust

d)

None of the above

23.

 What are typical sizes for the training, validation and testing sets?

a)

80% 10% 10%

b)

60% 20% 20%

c)

10% 80% 10%

d)

20% 20% 60%.

e)

50% 10% 40%

24.

How to calculate the recall?

a)

(tp + tn) / (tp + tn + fp + fn)

b)

tp/(tp + fp)

c)

tp/(tp+ fn)

d)

(tp + tn) / (tp + tn + fp)

25.

The correlation coefficient is used to determine:

a)

The strength of the relationship between the x and y variables

b)

A specific value of the y-variable given a specific value of the x-variable

c)

A specific value of the x-variable given a specific value of the y-variable

d)

All of the above

26.

How to calculate the accuracy?

a)

(tp + tn) / (tp + tn + fp + fn)

b)

tp/(tp+fp)

c)

tp /(tp + tn)

d)

(tp + tn) / (tp + tn + fp)

27.

Suppose you have fitted a complex regression model on a dataset. Now, you are using Ridge regression with tuning parameter lambda to reduce its complexity. Choose the option(s) below which describes the relationship of bias and variance with lambda.

a)

In case of very small lambda; bias is low, variance is low

b)

In case of very small lambda: bias is low, variance is high

c)

In case of very small lambda; bias is high, variance is low

d)

In case of very small lambda; bias is high, variance is high

28.

 Which of the following is not true about Machine Learning?

a)

Machine Learning was inspired by the learning process of human beings.

b)

Machine Learning models iteratively learn from data, and allow computers to find hidden insights.

c)

Machine Learning models help us in tasks such as object recognition, summarization, and recommendation systems.

d)

Machine Learning gives computers the ability to make decisions by writing down rules and methods and being explicitly programmed.

29.

How do you handle missing or corrupted data in a dataset?

a)

Drop missing rows or columns

b)

Replace missing values with mean/median/mode

c)

Assign a unique category to missing values

d)

All of the above

30.

What is the difference between supervised and unsupervised learning?

a)

Supervised learning uses labeled data, while unsupervised learning uses unlabeled data

b)

Both supervised and unsupervised learning use labeled data.

c)

Supervised learning is used for clustering, unsupervised for regression.

31.

What is the difference between supervised and unsupervised learning?

a)

Supervised learning uses labeled data, while unsupervised learning uses unlabeled data

b)

Both supervised and unsupervised learning use labeled data.

c)

Supervised learning is used for clustering, unsupervised for regression.

32.

  Provide an example of reinforcement learning.  

a)

Using decision trees to classify images.

b)

Training an AI to play chess by rewarding it for winning games.

c)

Predicting house prices based on labeled data

33.

Describe how supervised learning works.  

a)

It learns a function from labeled training data to make predictions on new data

b)

It makes decisions without any labeled data.

c)

It guesses predictions randomly and adjusts based on errors.

34.

Do you think machine learning is another name for artificial intelligence?  

a)

No, ML is a subset of AI focused on learning from data.

b)

Yes, AI is a subset of machine learning.

c)

Yes, they are the same thing.

35.

Why do we need to split the data into training and testing sets?  

a)

To evaluate the model’s performance on unseen data.

b)

To make the dataset larger

c)

To make sure the model only works on a small dataset.

36.

  Why do we need logistic regression?  

a)

For time-series forecasting.

b)

For binary and multi-class classification tasks.

c)

For dimensionality reduction.

37.

  Provide examples for each type of logistic regression.  

a)

Binary: Spam detection; Multinomial: Document classification; Ordinal: Customer satisfaction levels

b)

Decision trees examples only.

c)

Linear regression examples only.

38.

Why do we need linear regression?  

a)

To predict continuous numeric values based on input variable

b)

For classification tasks.

c)

For feature extraction.

39.

   What are evaluation metrics for classification problems?  

a)

Accuracy, Precision, Recall, F1-score, ROC-AUC

b)

R-squared, Mean Squared Error.

c)

A/B Testing, Click-through rates.

40.

  Why do we need a confusion matrix? Provide a detailed definition.  

a)

It helps visualize the performance of classification by showing TP, FP, FN, and TN counts.

b)

It shows the results of a regression model.

c)

It calculates the mean of predicted and actual values.

41.

What are evaluation metrics for linear regression?  

a)

Precision, Recall, F1-score.

b)

AUC, ROC Curve.

c)

Mean Absolute Error, Mean Squared Error, R-squared.

42.

   What is the difference between decision trees and random forests?  

a)

Random forests use fewer features than decision trees.

b)

Decision trees use more data points than random forests.

c)

Decision trees are single models; random forests combine many trees for better accuracy and stability.

43.

   Explain the structure of a decision tree  

a)

A table with rows and columns for data points.

b)

A linear regression model.

c)

A tree with nodes for decisions, branches for outcomes, and leaves for predictions

44.

What is the difference between precision and recall?  

a)

Precision: TP / (TP + FP); Recall: TP / (TP + FN)

b)

Precision and recall are the same.

c)

Precision: TN / (TN + FP); Recall: FP / (FP + FN)

45.

  Explain the cross-validation technique.  


a)

It uses a single fold for validation.

b)

Data is split into folds; the model trains on some folds and validates on the remaining one, rotating.

c)

The model is trained on the entire dataset at once.

46.

How does a random forest handle categorical variables?  

a)

It splits them using criteria like Gini impurity or information gain.

b)

It ignores categorical variables completely.

c)

It splits them using criteria like Gini impurity or information gain.

47.

   How does feature extraction work? Describe the steps involved.  

a)

Step 1: Collect data; Step 2: Clean data; Step 3: Transform raw features; Step 4: Select or extract key features.

b)

The raw data is used without any changes.

c)

Feature extraction happens automatically without any preparation.

48.

  What is the difference between computer vision and natural language processing?  

a)

CV processes images/videos; NLP processes text/language.

b)

CV processes audio; NLP processes images.

c)

Both fields process numerical data

49.

List 5 computer vision algorithms with descriptions  

a)

PCA: Image classification; LDA: Image classification; t-SNE: Image classification.

b)

SVM: Image classification; KNN: Image classification; Naive Bayes: Image classification.

c)

CNN: Feature extraction in images; YOLO: Real-time object detection; SIFT: Keypoint detection; R-CNN: Region proposals for object detection; Optical Flow: Motion tracking

50.

How do word embeddings work and where are they used?  

a)

They map words to vectors based on context; used in NLP tasks like translation and sentiment analysis

b)

They map words to random numbers.

c)

They convert words into images for processing.

51.

  How does text analysis help in real life?  

a)

Only useful for classifying text into categories.

b)

Spam filtering, sentiment detection, customer feedback analysis, chatbot development, topic modeling.

c)

Only helps with data compression.

52.

  What types of problems can Naive Bayes solve?  

a)

Text classification, spam detection, sentiment analysis, medical diagnosis

b)

Clustering problems.

c)

Regression problems.

53.

  What is sentiment analysis?  

a)

The process of categorizing text into topics.

b)

The process of converting text into numeric data.

c)

The process of determining if a piece of text is positive, negative, or neutral

54.

  How does tokenization work?  

a)

Splits text into words or phrases for processing.

b)

Groups words into predefined categories.

c)

Converts text into images.

55.

Real-life uses of computer vision?  

a)

Used for data normalization.

b)

Only used for photo editing.

c)

Face recognition, autonomous vehicles, medical imaging, quality inspection, surveillance

56.

  Describe SVM in detail.  

a)

SVM finds the average of all data points.

b)

SVM finds the optimal hyperplane that maximally separates classes in a dataset.

c)

SVM is used for time-series forecasting.

57.

How do recommender systems work? When are they used?  

a)

They analyze user behavior/preferences to suggest items. Used in e-commerce, streaming, and social media

b)

They only predict outcomes based on past behavior

c)

They classify users into fixed categories

58.

  Write an algorithm for KNN  

a)

1. Choose K; 2. Calculate distances to all points; 3. Sort distances; 4. Choose K nearest neighbors; 5. Vote for the most common label

b)

1. Choose K; 2. Take the average of distances; 3. Assign labels randomly

c)

1. Choose a single point; 2. Sort all points; 3. Select the farthest neighbor.

59.

  What is the purpose of SVM?  

a)

To classify data by finding the best boundary between categories.

b)

To cluster similar data points together

c)

To predict continuous values

60.

What is text vectorization and how does it work?  

a)

Converts text into numeric form using methods like Bag of Words or TF-IDF

b)

Uses neural networks to interpret text.

c)

Converts text into images

61.

Example of SVM with detailed description.  

a)

Email classification using decision trees.

b)

Email classification: SVM separates spam vs non-spam based on word vectors.

c)

Email classification using KNN.

62.

  List 3 dimensionality reduction techniques besides PCA.  

a)

t-SNE: Non-linear dimensionality reduction; LDA: Projects data for classification; Autoencoders: Neural network-based reduction

b)

K-means: Clustering; Naive Bayes: Classification; SVM: Classification.

c)

Decision Trees: Classification; Linear Regression: Prediction.

63.

  Describe K-means in one sentence.  

a)

It clusters data by assigning points to the nearest of K centroids

b)

It predicts continuous values based on input data.

c)

It generates random clusters.

64.

  What is the architecture of autoencoders? How do they work?  

a)

Encoder randomly selects data; decoder generates predictions.

b)

Encoder compresses input; decoder reconstructs it, useful for reducing dimensionality.

c)

Autoencoders perform classification.

65.

  What is KNN and where can it be used?  

a)

KNN is a classification algorithm based on distance; used in pattern recognition and recommender systems.

b)

KNN is used for time-series forecasting.

c)

KNN is used only in clustering

66.

Which of the following is not Machine Learning techniques?

1 point

Classification and Regression

Clustering

Numpy, Scipy and Scikit-Learn

Anomaly Detection and Recommendation Systems

a)

Numpy, Scipy and Scikit-Learn

b)

Classification and Regression

c)

Clustering

67.

Which is not a sample of classification problems?

a)

To predict the amount of money a customer will spend in one year

b)

To predict whether a customer switches to another provider or brand

c)

To predict the the category to which customer belongs to

d)

To predict whether a customer responds to a particular advertising campaign or not

68.

Suppose you are working on weather prediction, and use a learning algorithm to predict tomorrow's temperature (in degrees Centigrade/Fahrenheit). Would you treat this as a classification or a regression problem?

a)

Regression

b)

Classification

c)

Clustering

69.

What are independent variables?

a)

The features of our dataset

b)

The values that interfere in the value we want to predict

c)

The parameters of the regression algorithm

d)

The value we want to predict

70.

What makes the supervised model different from unsupervised?

a)

Differences are only on the name b. Different libraries are used

b)

In the depth of ML. models

c)

Existence of ground truth labels