Enrolment No. /Seat No.
: ______________
GUJARAT TECHNOLOGICAL UNIVERSITY
MCA – SEMESTER III- EXAMINATION –WINTER-2024
Subject Code:639402 Date: 20/11/2024
Subject Name: Machine Learning
Time:10:30 AM TO 01:00 PM Total Marks: 70
Instructions:
1. Attempt all questions.
2. Make Suitable assumptions wherever necessary.
3. Figures to the right indicate full marks.
4. Use of simple calculators and non-programmable scientific calculators are permitted.
Q.1 (a) Answer following: 03
1. Define human learning.
2. Weather forecasting is _____________ task. (Regression/Classification)
3. Define ROC.
(b) Discuss the use of histogram in effective visualization of attributes with example. 04
(c) Explain types of data supported by machine learning. 07
Q.2 (a) Write short note on bootstrap sampling. 04
(b) Explain under-fitting and over-fitting in machine learning model. 03
(c) Define feature construction. Discuss the need of feature construction with an 07
example.
OR
(c) Discuss the measures of feature relevance and redundancy. 07
Q.3 (a) Explain data quality and data remediation in detail. 07
(b) Write down the limitations of holdout method. Explain k-fold cross validation 07
method.
OR
Q.3 (a) Discuss bagging and boosting in detail. 07
(b) Explain feature selection process in detail. List out the feature selection approaches. 07
Q.4 (a) Differentiate supervised learning and unsupervised learning. 07
(b) Explain decision tree algorithm with its applications, strengths and weaknesses. 07
OR
Q.4 (a) List out the classification learning steps. Explain in detail. 07
(b) Define regression analysis. Discuss the assumptions made in regression analysis. 07
Q.5 (a) Write short note on: 07
1. Maximum Margin Hyperplane 2.DBSCAN
(b) Explain logistic regression in detail. 07
OR
Q.5 (a) Write and discuss apriori algorithm for association rule learning. 07
(b) Discuss various partition based clustering techniques in detail. 07
*************
1
Seat No.: ________ Enrolment No.______________
GUJARAT TECHNOLOGICAL UNIVERSITY
MCA– SEMESTER III- EXAMINATION –WINTER-2023
Subject Code:639402 Date: 02/12/2023
Subject Name: Machine Learning
Time: 10:30 AM TO 01:00 PM Total Marks: 70
Instructions:
1. Attempt all questions.
2. Make Suitable assumptions wherever necessary.
3. Figures to the right indicate full marks.
4. Use of simple calculators and non-programmable scientific calculators are permitted.
Q.1 (a) Define following terms. 03
1. Information gain
2. DBSCAN
3. Reinforcement learning
(b) What is human learning? Explain types of human learning. 04
(c) Discuss the applications and tools of machine learning. 07
Q.2 (a) Explain qualitative and quantitative data in machine learning. 03
(b) What are activities involved in machine learning? 04
(c) Explain k-fold cross validation method in detail 07
OR
(c) Briefly explain overall feature selection process. 07
Q.3 (a) Discuss singular value decomposition algorithm. 07
(b) What is feature transformation? Explain feature construction process in detail. 07
OR
Q.3 (a) Define outliers. Can we handle outliers and missing values in data? Explain in brief. 07
(b) Define over-fitting & under-fitting. Discuss the errors in learning. 07
Q.4 (a) Briefly explain classification learning steps. 07
(b) Explain multiple linear regression technique in detail. 07
OR
Q.4 (a) What is ensembling? Explain random forest model in brief. 07
(b) Differentiate supervised learning and unsupervised learning with reference to 07
various aspects.
Q.5 (a) Explain k-means clustering algorithm in detail. 07
(b) What is regression? Discuss assumptions in regression analysis. 07
OR
Q.5 (a) What is association rule? Discuss the concept of support and confidence to justify 07
the strength of association rule with appropriate example.
(b) Explain k-medoids clustering algorithm in detail. 07
*************
1
Seat No.: ________ Enrolment No.______________
GUJARAT TECHNOLOGICAL UNIVERSITY
MCA – SEMESTER III- EXAMINATION –WINTER-2022
Subject Code: 639402 Date: 28/12/2022
Subject Name: Machine Learning
Time: 10:30 AM TO 01:00 PM Total Marks: 70
Instructions:
1. Attempt all questions.
2. Make Suitable assumptions wherever necessary.
3. Figures to the right indicate full marks.
1.
Q.1 (a) Answer the following questions. 07
(1) Define : Machine Learning
(2) What are the three parts in which machine learning process is divided?
(3) What is Euclidian distance? Write formula to calculate it.
(4) Write full form of PCA and explain it in brief.
(5) Which kind of learning algorithm skips the abstraction and generalization
process?
(6) Write Bayes’probability rule.
(7) Which kind of learning is useful to find out patterns in data set?
(b) Answer TRUE/FALSE with justification 07
(1) Interval and ratio attributes are discrete data.
(2) Overfitting the model means emulating training data too closely.
(3) K-nearest neighbor is a parametric machine learning algorithm.
(4) The probability that a particular hypothesis holds for a data set based on
the Prior is called independent probability
(5) Hierarchical method is a type of clustering.
(6) Reinforcement learning model uses reward and punishment.
(7) Supervised learning is known as descriptive learning.
.
Q.2 (a) Explain the applicability of machine learning. Why machine learning is necessary 07
to solve real world problems in real time?
(b) Explain the machine learning activities in detail. 07
OR
(b) Give comparative explanation of all three types of machine learning techniques 07
by considering following points :
1. When to use which model
2. Training data
3. Performance measure
4. Types of each model
5. Example algorithms
6. Applications
Q.3 (a) Explain basic types of data in machine learning. 07
(b) Explain holdout and k-fold cross validation for supervised learning model. 07
OR
Q.3 (a) Explain under fit, over fit and balanced fit. How it will affect bias – variance trade 07
off? Explain it diagrammatically.
Page 1 of 2
(b) Explain feature transformation in detail with example. 07
Q.4 (a) Explain decision tree algorithm in detail 07
(b) Explain linear regression model for prediction in detail. 07
OR
Q.4 (a) Explain Bayes probability model with prior, posterior and likelihood in detail. 07
(b) Explain kNN algorithm with strength and weakness. Which is the popular 07
application area of kNN?
Q.5 (a) Explain K means algorithm in detail. 07
(b) Explain classification model steps using diagram. 07
OR
Q.5 (a) What is clustering? Explain application areas in which clustering used. 07
(b) Explain market basket analysis using association rule. 07
*************
Page 2 of 2
Seat No.: ________ Enrolment No.______________
GUJARAT TECHNOLOGICAL UNIVERSITY
MCA – SEMESTER -III EXAMINATION –WINTER-2021
Subject Code: 639402 Date: 28/12/2021
Subject Name: Machine Learning
Time: 10:30 AM TO 01:00 PM Total Marks: 70
Instructions:
1. Attempt all questions.
2. Make Suitable assumptions wherever necessary.
3. Figures to the right indicate full marks.
Q.1 (a) Explain following terms. 07
1) F1 score
2) Root mean square error
3) Confusion matrix
4) AUC
5) ROC
6) Accuracy
7) Recall
(b) List the tools for Machine Learning application development with detail. 07
Q.2 (a) Explain Different types of Machine learning. 07
(b) How to find Nearest Neighbors in KNN algorithm. 07
OR
(b) Discuss Data type in context of Machine learning. 07
Q.3 (a) Explain PCA with appropriate example. 07
(b) Write short note on Data pre-processing. 07
OR
Q.3 (a) State difference between cross validation and k-fold. 07
(b) Explain Data preprocessing in machine learning. 07
Q.4 (a) What is over fitting and under fitting explain with an appropriate example and figure. 07
(b) Explain Decision Tree algorithm. 07
OR
Q.4 (a) Explain Artificial Neural Network with suitable example. 07
(b) Explain SVM algorithm with appropriate example. 07
Q.5 (a) Explain Association Rules and how it help to grow sales? 07
(b) Explain K-means algorithms with an appropriate example. 07
OR
Q.5 (a) What is Naïve Bayes classifier? Narrate Principle of Naive Bayes Classifier. 07
(b) What is Regression? Explain its types in details. 07
*************
