Seat No.: ________ Enrolment No.
___________
GUJARAT TECHNOLOGICAL UNIVERSITY
BE - SEMESTER–VII (NEW) EXAMINATION – WINTER 2023
Subject Code:3171114 Date:08-12-2023
Subject Name: Introduction of 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. Simple and non-programmable scientific calculators are allowed.
MARKS
Q.1 (a) Give comparison between Supervised Learning and Unsupervised 03
Learning.
(b) Give reasons for overfitting and provide options to resolve overfitting 04
problem.
(c) Discuss K- Nearest Neighborhood classification method with its advantages 07
and disadvantages.
Q.2 (a) Write down names of three approaches for feature selection. 03
(b) At a certain University,4% of men are above 6 feet tall and 1% of women 04
are over 6 feet tall. The total student population is divided in the ratio of 3:2
in favor of woman. If a student is selected at random from among all those
over six feet tall, what is the probability that the student is woman?
(c) Write three techniques to measure feature redundancy and explain each in 07
detail.
OR
(c) A mechanical factory production line is manufacturing bolts using three 07
machines, A, B and C. The total output, machine A is responsible for 25%,
machine B for 35% and machine C for the rest. The machines that 5% of
the output from machine A is defective, 4% from machine B and 2% from
machine C. A bolt is chosen at random from the production line and found
to be defective. What is the probability that it came from (1) Machine A (2)
Machine B (3) Machine C.
Q.3 (a) Write down applications of Support Vector Machine (SVM) classifier. 03
(b) Give advantages and disadvantages of K – means Clsutering algorithm. 04
(c) Differentiate between Clustering and Classification. 07
OR
Q.3 (a) Write down desirable properties of Clustering Algorithm. 03
(b) Give a comparison between SVM and Neural Network. 04
(c) Explain the need for Kernel Method in SVM and explain use of Kernel 07
Method in SVM.
Q.4 (a) Write advantages of Neural Network. 03
(b) Write down the steps for the selection of number of hidden units for 04
backpropagation method.
(c) Explain Adaptive Linear Neuron (ADALINE) Network Model in detail. 07
OR
Q.4 (a) Write application of Neural Network. 03
(b) Write the advantages and disadvantages of Backpropagation method. 04
(c) Explain Multi Layer Feed Forward Network in detail. 07
Q.5 (a) Define Cross Validation. 03
(b) Explain Variance reduction and Bias reduction in the context of Ensemble 04
1
Method.
(c) Explain Vapnik- Chervonenkis (VC) dimension in detail. 07
OR
Q.5 (a) Write equations for Accuracy rate, recall, and Specificity in terms of True 03
Positive (TP), true Negative (TN), False positive (FP), and False Negative
(FN).
(b) Explain Voting and Stacking approaches for Combining Ensemble 04
methods.
(c) Write down the steps for Bagging and mention its advantages and 07
disadvantages.
*************
