BTech (CS/IT) VI Semester Examination, 2020
CS 317: Artificial Intelligence and Machine Learning
Maximum Marks - 60
The question paper is divided into three Sections. Students are required to attempt five questions
in all, selecting not more than two questions from each Section.
All questions carry equal marks.
SECTION A
1. (a) After the initial setbacks, researchers observed that intelligence requires knowledge. What
disadvantages does knowledge possess? (6)
(b) What do you understand by informed state space?
https://www.cs.iusb.edu/~danav/teach/c463/5_informed_search.html (3)
(c) State the conditions under which A* is admissible
https://www.ics.uci.edu/~kkask/Fall-2014%20CS271/slides/03-InformedHeuristicSearch.pdf
(pg 36)
2. (a) Apply Alpha-Beta pruning on following example considering first node as MAX.
(6)
https://www.ques10.com/p/48089/alpha-beta-pruning-1/
(b) Why are data reduction techniques applied on a given dataset? How can we handle missing values in a
dataset https://hub.packtpub.com/understanding-data-reduction-patterns/#:~:text=Data%20reduction
%20aims%20to%20obtain,volume%20than%20the%20original%20dataset.
Video (6)
3. Consider the following statements:
(i) Ram was a man
(ii) Valmiki was a saint
(iii) Ravan was a ruler
(iv) All Hindus were either loyal to Ravan or hated him
(v) Everyone is loyal to someone
(vi) People only try to assassinate rulers they are not loyal to
(vii) All saints are Hindu
(viii) Ram tried to assassinate Ravan
http://www.cs.toronto.edu/~edelisle/384/f14/Lectures/LogicExample.pdf
(a) Convert these statements into facts and rules (6)
(b) Using resolution answer the question “Did Ram hated Ravan” (6)
SECTION B
4. (a) For a SunBurn dataset given below, construct a decision tree.
http://www2.cs.uregina.ca/~dbd/cs831/notes/ml/dtrees/dt_prob1.html
Name Hair Height Weight Location Class
Name Hair Height Weight Location Class
Sunita blonde average light no yes
anit blonde tall average yes no
kavita brown short average yes no
sushma blonde short average no yes
xavier red average heavy no yes
balaji brown tall heavy no no
ramesh brown average heavy no no
swetha blonde short light yes no
In this dataset, Name, Hair, Height, Weight and Location are Dependent Variables (Predictors) and
Class is the independent variable (target). (6)
(b) The values of independent variable x and dependent value y are given below:
X Y
1 0:0319
0 0.8692
1 1.9566
2 3.0343
Find the least square regression line y=ax+b. Estimate the value of y when x is 10. (6)
https://www.analyzemath.com/statistics/linear_regr ession.html
5 (a) Consider the following dataset of stolen vehicles. Colour, Type and Origin are dependent variables
and Stolen is an independent variable.
Colour Type Origin Stolen
Red Sports Domestic Yes
Red Sports Domestic No
Red Sports Domestic Yes
Yellow Sports Domestic No
Yellow Sports Imported Yes
Yellow SUV Imported No
Yellow SUV Imported Yes
Yellow SUV Domestic No
Red SUV Imported No
Red Sports Imported Yes
Using Naïve Bayes classifier, classify the new data (Colour=Red, Type=SUV, Origin=Domestic). (6)
http://csci.viu.ca/~barskym/teaching/DM2012/tests/Quiz%206_solution.pdf
(b)Find out a problem which cannot be solved easily using the architectures familiar to you. Suggest
anarchitecture to solve this. Why do you think that this architecture can solve the problem? Suggest
a procedure to derive the learning rule(s). (6)
6 (a) Consider the following dataset for loan classification. Age and Loan Amount are dependent
variables and Default? is an independent variable.
Age Loan Default?
25 40000 N
35 60000 N
45 80000 N
20 20000 N
35 120000 N
52 18000 N
23 95000 Y
40 62000 Y
60 100000 Y
48 220000 Y
33 150000 Y
Using a K-Nearest Neighbour classifier, classify the new data (Age=47 and Loan Amount = Rs ). Use
Euclidian Distance for computation. Classify the new data for 1 and 5 nearest neighbours.
(6)
https://www.youtube.com/watch?v=upescYWo1xg&t=768s
(b) Consider the following confusion matrix for 3 variables
Predicted
A’ B’ C’
A 25 5 2
Actual
B 3 32 4
C 1 0 15
https://www.youtube.com/watch?v=FAr2GmWNbT0
Calculate Precision, Recall, F-Measure and Accuracy for Class B
https://www.geeksforgeeks.org/confusion-matrix-machine-learning/ (6)
SECTIONC
7. (a)Enumerate the modalities of Reinforcement Learning for a Game of Chess (6)
http://citeseerx.ist.psu.edu/viewdoc/download?doi=10.1.1.109.810&rep=rep1&type=pd
(b) Why do we need to perform cross-validation while training our models? How can it improve the
performance of the models? (6)
https://towardsdatascience.com/why-and-how-to-cross-validate-a-model-d6424b45261f#:~:text=K
%2DFolds%20Cross%20Validation%3A&text=Because%20it%20ensures%20that%20every,method
%20follows%20the%20below%20steps.
8. (a) Consider the following data.
2, 11, 8, 13, 10, 2, 13, 5, 4, 12, 6, 10, 11, 6, 7, 13, 1
Using K-Means Clustering, categorize this data into 3 clusters. Assume random initial centroid
values and Euclidian distance function. Show the working for each iteration.
https://www.youtube.com/watch?v=fqifimCNfKk (6)
(b) Consider the following dataset
X1 X2
12 10
15 14
13 11
Find the distance between X and Y data points where Y1=9 and Y2=12. Compute the distance for
Manhattan Distance and Makowski Distance with q=5.
https://www.youtube.com/watch?v=JHdOoEAyk5g
(6)
9. Consider the following corpus
<s>Banasthali Vidyapith is a University with a difference </s>
<s> This is a fully residential University </s>
<s>Banasthali Vidyapith is in India </s>
(a) Generate a Markov Chain of Order 1 for the corpus (8)
(b) Check the validity of the sentence<s>Banasthali Vidyapith is a fully residential University in
India </s>using the model developed (4)
