DR.

BABASAHEB AMBEDKAR TECHNOLOGICAL UNIVERSITY, LONERE

Supplementary Winter Examination – 2024
Course:B.Tech Branch :Computer Engineering/Computer Science and Engineering
Semester : VI
Subject Code & Name: BTCOC603_Y23 Machine Learning
Max Marks: 60 Date: 23/12/2024 Duration: 3 Hr.
Instructions to the Students:
1. Each question carries 12 marks.
2. Question No. 1 will be compulsory and include objective-type questions.
3. Candidates are required to attempt any four questions from Question No. 2 to Question No. 6.
4. The level of question/expected answer as per OBE or the Course Outcome (CO) on which the
question is based is mentioned in ( ) in front of the question.
5. Use of non-programmable scientific calculators is allowed.
6. Assume suitable data wherever necessary and mention it clearly.
(Level/CO) Marks
Q. 1 Objective type questions. (Compulsory Question) 12
1 What is the main purpose of cross-validation in machine learning? 1

a. To measure b. To tune c. To evaluate d. To reduce

training hyperparameters the model's dimensionality
accuracy performance
on unseen
data
2 Logistic Regression is primarily used for: 1
a. Regression b. Classification c. Clustering d.
problems problems problems Dimensionality
reduction
3 What is the main limitation of a perceptron? 1
a) It cannot b) It requires a c) It is prone to d) It uses too
classify non- large amount of overfitting many
linearly data resources
separable data

4 Which of the following optimizes weights during backpropagation? 1

a) Support b) Gradient c) Random d) k-Means
Vector Descent Forest Clustering
Machine
5 In PAC learning, the goal is to: 1
a) Learn a b) Learn a model c) Learn a d) Learn a
model with with probable model with deterministic
zero error approximately infinite model
correct hypothesis
predictions space
6 The VC dimension of a model signifies: 1

Page 1
 a) The number b) The size of the
c) The capacity d) The number
of dimensions training data of the model of iterations in
in the data required to classify training
different
datasets
7 What is the primary objective of k-means clustering? 1
a) To classify b) To minimize c) To maximize d) To assign
data into the distance the separation each data
predefined between cluster between point to the
categories centroids and clusters nearest
points in the decision
cluster boundary

8 What metric is commonly used to measure the distance in k-means 1

clustering?
a) Manhattan b) Cosine c) Euclidean d) Jaccard
distance similarity distance index
9 What type of clustering does a Dendrogram represent? 1
a) Partitional b) Hierarchical c) Spectral d) Density-
clustering clustering clustering based
clustering
10 What is Ensemble Learning? 1
a) A techniqueb) A method of c) A process to d) A clustering
to increase the
combining select the technique to
dataset size multiple models best- group similar
to improve performing data points
performance single model
11 Which algorithm is an example of the boosting method? 1
a) Random b) AdaBoost c) k-Nearest d) Support
Forest Neighbors Vector
Machine
12 In a Decision Tree, leaf nodes represent: 1
a) Decision b) Final c) d) Root of the
points for outcomes or Intermediate tree
further splits predictions computations

Q. 2 Solve the following. 12

A) Explain confusion matrix for classification problem. Understand 6
B) Write algorithm for top down induction of decision tree (ID3). Understand 6

Page 2
Q.3 Solve the following. 12
A) A dataset is given below: Apply 6
Weather Car Class
sunny working go-out
rainy broken go-out
sunny working go-out
sunny working go-out
sunny working go-out
rainy broken stay-home
rainy broken stay-home
sunny working stay-home
sunny broken stay-home
rainy broken stay-home
Apply Naïve Bays Classification algorithm and calculate the
probabilities for the instance “sunny working” and classify the given
instance.
B) How linear SVM works? Explain with example Understand 6

Q. 4 Solve Any Two of the following. 12

A) Draw multilayer feed forward back propagation neural network and Understand 6
explain.
B) Explain Convolutional Neural Network for image classification. Apply 6
C) How perceptron works? Explain with diagram. Understand 6

Q.5 Solve Any Two of the following. 12

A) Apply Find-S algorithm to following dataset and find the most specific Apply 6
hypothesis.

B) Explain Ensemble Learning in detail. Understand 6

C) Explain the concept of Bagging and Boosting Understand 6

Page 3
Q. 6 Solve Any Two of the following. 12
A) What do you mean by dendrogram? Explain. Remember 6
B) Write Nearest Neighbor Clustering Algorithm. Understand 6
C) Explain Kmeans clustering algorithm with example. Understand 6
*** End ***

Page 4
 DR. BABASAHEB AMBEDKAR TECHNOLOGICAL UNIVERSITY, LONERE
Regular & Supplementary Summer 2024
Course: B. Tech. Branch : Computer Engineering and Computer Sci. & Engg.
Semester :VI Subject Code & Name: BTCOC603_Y23 Machine Learning
Max Marks: 60 Date: 19/06/2024 Duration: 3 Hrs
Instructions to the Students:
1. All the questions are compulsory.
2. The level of question/expected answer as per OBE or the Course Outcome (CO)
on which the question is based is mentioned in ( ) in front of the question.
3. Use of non-programmable scientific calculators is allowed.
4. Assume suitable data wherever necessary and mention it clearly.
(Level/CO) Marks
Q. 1 Solve Any Two of the following. 12
A) Differentiate between Supervised and Unsupervised learning. Analyse/CO1 6
B) Explain Decision Tree Algorithm with Example. Understand/CO1 6
C) Predict the class for (?) in the given below dataset using KNN algorithm. Evaluate/CO1 6
Assume K=3.

BRIGHTNESS SATURATION CLASS

40 20 Red
50 50 Blue
60 90 Blue
10 25 Red
70 70 Blue
60 10 Red
25 80 Blue
20 35 ?

Q.2 Solve Any Two of the following. 12

A) What is curse of Dimensionality? What are measures to resolve it? Understand/CO2 6
B) Explain Logistic Regression with example. Remember/CO2 6
C) Consider the training data in the following table Apply/CO2 6

Find the class label for the following day by applying naïve Bayesian
classification to above dataset.
X = (Humidity=L, Sunny=N, Wind=W)
Q.3 Solve Any Two of the following. 12
A) How perceptron works? Explain. Understand/CO3 6
B) What is backpropagation? Explain in brief with neat diagram. Understand/CO3 6
C) Explain the Architecture of Convolutional Neural Network. Understand/CO3 6

Q.4 Solve Any Two of the following. 12

A) Explain the concept of Probably Approximately Correct learning Remember/CO4 6

B) Apply/CO4 6
Consider the following data set having the data about which particular seeds are
poisonous.

Apply the Find-S algorithm and find the final hypothesis.

C) What is ensemble learning? Explain bagging and boosting. Understand/CO4 6

Q. 5 Solve Any Two of the following. 12

A) What is unsupervised machine learning? Explain with suitable example Understand/CO5 6
B) Apply/CO5 6
Cluster the following eight points (with (x, y) representing locations) into three
clusters:
A1(2, 10), A2(2, 5), A3(8, 4), A4(5, 8), A5(7, 5), A6(6, 4), A7(1, 2), A8(4, 9)
Initial cluster centers are: A1(2, 10), A4(5, 8) and A7(1, 2).
C) Explain Agglomerative Algorithm in Hierarchical Clustering in detail. Understand/CO5 6
*** End ***
 DR. BABASAHEB AMBEDKAR TECHNOLOGICAL UNIVERSITY, LONERE
Regular & Supplementary Winter Examination-2023
Course: B. Tech. Branch : CSE(AI&ML)/AI&DS/AI Semester :V
Subject Code & Name: BTAIC502 Machine Learning
Max Marks: 60 Date:03-01-24 Duration: 3 Hr.
Instructions to the Students:
1. All the questions are compulsory.
2. The level of question/expected answer as per OBE or the Course Outcome (CO) on
which the question is based is mentioned in ( ) in front of the question.
3. Use of non-programmable scientific calculators is allowed.
4. Assume suitable data wherever necessary and mention it clearly.
(Level/CO) Marks
Q. 1 Solve Any Two of the following. 12
A) Define Machine Learning. Describe the application of Machine Learning Understand 6
B) Compare and contrast the Classification, Regression and Clustering on the Analyze 6
basis of following Parameter
• Type
• Basic
• Includes anticipation of
• Characteristics of anticipated data
• Procedure for calculating
• Algorithms
C) Explain the types of Machine Learning with suitable Diagram and Understand 6
Example

Q.2 Solve Any Two of the following. 12

A) Explain the Confusion Matrix with example and state the nedd of Understand 6
confusion matrix
B) For the given confusion matrix Calculate Apply 6
N=200 Prediction = No Prediction = Yes
Actual = No 60 10
Prediction = Yes 5 125
1. Accuracy
2. Error Rate
3. Precision
4. Recall
5. Specificity
6. F1 Score
 C) Explain the Performance Metrics for Regression Problems- Mean Absolute Apply 6
Error (MAE), Mean Square Error (MSE), R Squared (R2)
And for the following Table Calculate
1. MAE
2. MSE
3. RMSE
Ticket Actual Predicted
# Price Price

1 250 265
2 110 140
3 500 480
4 200 215
5 330 290
6 490 515
7 670 750
8 210 210
9 435 420
10 375 285

Q. 3 Solve Any Two of the following. 12

A) What is logistic regression? Explain the steps in Logistic Regression Understand 6
Learning. Also give the cost function of Logistic Regression
B) Explain the Gradient Descent and how it helpful to maximize the learning Understand 6
rate in regression
C) A. The values of y and their corresponding values of y are shown in Apply 6
the table below
x 0 1 2 3 4
y 2 3 5 4 6
a) Find the least square regression line y = B1 x + B0
b) Estimate the value of y when x = 10.

Q.4 Solve Any Two of the following. 12

A) Consider the following dataset S in table for question where each record 6
represents the age, income and is a student or not. And we need to classify
it as buyers/non-buyers of computer.
 1. Calculate the information Gain(S,income)?
2. Calculate the information Gain(S,Credit_score)?
3. Calculate the information Gain(S,student)?
B) Explain Overfitting and Pruning with respect to Decision Tree Understand 6
C) Explain the Random forest Algorithm with examples. Understand 6

Q. 5 Solve Any Two of the following. 12

A) For the following Dataset use Naïve Bayes Classifier to classify following 6
problem

Classify

B) Explain Kernel Trick in SVM? Kernel Trick is helpful to solve non- Understand 6
linearly separable problem in SVM. Justify
C) Explain the working of KNN Algorithm Apply 6
For the Given Dataset use to Classify Dog, Pig and Cat with given features.
Height Width Class
0.1 0.1 cat
0.2 0.5 cat
0.3 0.2 cat
0.4 0.3 cat
 0.5 0.6 cat
0.6 0.1 Pig
0.7 0.2 Pig
0.8 0.5 Pig
0.9 0.3 Pig
0.6 0.9 Dog
0.7 0.5 Dog
0.8 0.6 Dog
0.9 0.7 Dog

Use 3-NN and 5 NN to find the Class for following unknown data Use
Euclidian Distance as Distance metric for given dataset
Height Width Class
0.6 0.6 ???
*** End ***
 DR. BABASAHEB AMBEDKAR TECHNOLOGICAL UNIVERSITY, LONERE
Summer Regular Examination – 2023
Course: B. Tech. Branch :CSE/Computer Engineering Semester : VI
Subject Code & Name: BTCOC603 Machine Learning
Max Marks: 60 Date:17/07/2023 Duration: 3 Hr.
Instructions to the Students:
1. All the questions are compulsory.
2. The level of question/expected answer as per OBE or the Course Outcome (CO) on
which the question is based is mentioned in ( ) in front of the question.
3. Use of non-programmable scientific calculators is allowed.
4. Assume suitable data wherever necessary and mention it clearly.
(Level/CO) Marks
Q. 1 Solve Any Two of the following. 12
A) Define machine learning. Explain its common areas of applications. (Remember) 6
B) Describe working of decision tree with suitable example. (Apply) 6
C) State the purpose of confusion metrics. Elaborate various terms (Understand) 6
associated with it.

Q.2 Solve Any Two of the following. 12

A) State Bayestheorem. Demonstrateit with suitable example. (Apply) 6
B) With respect to SVM explain the terms: 1. Hyperplane 2. Maximum (Understand) 6
Margin Hyperplane (MMH) 3. Support Vector.
C) Differentiate between linear and non-linear SVM. (Analyze) 6

Q. 3 Solve Any Two of the following. 12

A) Compare between Biological Neural Network (BNN) and Artificial (Analyze) 6
Neural Network (ANN).
B) Explain reinforcement learning in Artificial Neural Network (ANN). (Understand) 6
C) Describe feedforward and feedback neural network with proper (Understand) 6
diagram.

Q.4 Solve Any Two of the following. 12

A) Explain concept of VC dimensions with example. (Remember) 6
B) Discuss Ensembled Learning. State applications of ensembled learning. (Understand) 6
C) Describe terms: Bagging, Boosting and Stacking. (Understand) 6

Q. 5 Solve Any Two of the following. 12

A) Explain clustering with example. State need of clustering. (Understand) 6
B) State the working of K-means clustering algorithm. (Remember) 6
C) Differentiate between Agglomerative and Divisive hierarchical (Analyze) 6
clustering.
*** End ***
 DR. BABASAHEB AMBEDKAR TECHNOLOGICAL UNIVERSITY, LONERE
Supplementary Semester Examination – January 2023
Course: B. Tech. Branch : CE / CSE / CS Semester : V
Subject Code & Name: Machine Learning [BTCOC503]
Max Marks: 60 Date: Duration: 3 Hrs.

Instructions to the Students:

1. All the questions are compulsory.
2. The level of question/expected answer as per OBE or the Course Outcome (CO) on which the question
is based is mentioned in ( ) in front of the question.
3. Use of non-programmable scientific calculators is allowed.
4. Assume suitable data wherever necessary and mention it clearly.
(Level/
Marks
CO)

Q.1 Solve the following questions. [12]

A) Differentiate between Supervised Unsupervised Machine Learning approaches with 2

suitable example.
B) How do you choose best split in the Decision Tree algorithm 2
C) Write Short note on: 2
(a) Cross Validation
(b) Inductive bias

Q.2 Attempt the following questions. [12]

A) Write a note on Bayes theorem and illustrate maximum likelihood method for predicting 2
probabilities in Bayesian learning with an example.
B) What is instance based learning? Explain importance of feature reduction while solving 1
problem using machine learning technique.

Q.3 Solve Any Two of the following. [12]

A) How to find right Hyperplane in Support Vector Machine explain with suitable Example. 2
B) Explain Logistic Regression on the basis of following points: 2
(a) Features of Logistic regression
(b) Types of Logistic Regression.
C) Differencentiate between Multinomial Logistic Regression and Binomial Logistic 2
Regression.

Q.4 Solve any TWO questions of the following. [12]

A) Differentiate between machine learning and Deep Learning. 2

B) Explain basic architecture of multi layer network. Explain back-propagation, in multi layer 1
network.
 C) Write note on: 1
1. PAC Learning Model
2. Ensemble Learning

Q.5 Solve Any Two of the following. [12]

A) How does k-means clustering algorithm works? 2

B) How to choose optimal value of k in k-means clustering technique? 1
C) Write note on: 2
(a) adaptive hierarchical clustering
(b) Gaussian mixture model
*** End ***