Seat No.: ________ Enrolment No.
___________
GUJARAT TECHNOLOGICAL UNIVERSITY
BE - SEMESTER–VII (NEW) EXAMINATION – WINTER 2022
Subject Code:3170924 Date:05-01-2023
Subject Name:AI and 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) With reference to machine learning, explain the meaning of the term 3
‘inductive bias’.
(b) Define and explain supervised and unsupervised learning. 4
(c) Give a brief review of the history of Artificial Intelligence. 7
Q.2 (a) State the difference between fuzzy and crisp logic with the help of an 3
example
(b) What is cross validation? Explain k-fold cross validation and discuss how 4
final accuracy is calculated in k-fold cross validation?
(c) Explain the concept of Artificial neurons. Discuss the different types of 7
activation functions employed in neural networks
OR
(c) Explain back propagation neural networks. Discuss the steps involved in 7
back propagation algorithm.
Q.3 (a) Define feature selection in machine learning. Enlist the steps involved. 3
(b) Explain linear regression method used for prediction of output 4
(c) In Mamdani approach, assume that two rules are going to be fired for a set 7
of inputs. The fuzzified outputs of two fired rules are shown in Fig. A and
Fig. B. Find the defuzzified output using Centre of Sums method.
OR
Q.3 (a) What is feature extraction? Explain how dimensionality reduction can be 3
achieved using feature extraction technique
(b) Explain logistic regression method. Discuss how logistic regression 4
differs from linear regression.
(c) Discuss the different types of membership functions used in fuzzy logic 7
Q.4 (a) Explain why Genetic Algorithms are less likely to get stuck in local 3
optimum?
(b) What is the purpose of selection (reproduction) operator in Genetic 4
Algorithm? Explain any one selection operator in detail.
(c) With the help of flowchart, explain the working of Genetic Algorithms 7
OR
Q.4 (a) What is collaborative filtering? Why it is used in recommender systems? 3
(b) The decision variables x1 and x2 in Genetic Algorithms are represented 4
by x1 = 110011 and x2 = 001101. Find the value of x1 and x2 if the limits
on decision variables for x1 is between 0 to 5 and for x2 is between 2 to
7.5
(c) Explain any one Genetic Algorithm based application 7
Q.5 (a) What are decision trees? Explain the meaning of decision node and leaf 3
node.
(b) How is entropy calculated in decision trees? What would be the value of 4
entropy if we have full knowledge about the system?
(c) What is support vector machine? Also explain the concept of hyperplanes, 7
support vectors and the kernel trick in SVM
OR
Q.5 (a) Is clustering approach supervised or unsupervised method of learning? 3
Explain with the help of appropriate example.
(b) Explain agglomerative hierarchical clustering in brief. 4
(c) Explain K-means clustering in detail. Discuss any one method to decide 7
upon the number of clustersrequired for a particular problem.
