A1.

Explain with suitable example advantages of Bayesian approach over classical

approaches to probability.
A2. Explain in detail Principal Component Analysis for Dimensionality Reduction.
A3. Write short note on : (i) Machine Learning applications (ii) Issues in decision trees.
A4. Explain key terminologies of Support Vector Machine.
A5. What are the key tasks in machine learning.
A6. Explain the concept behind linear regression.
A7. Explain in brief Reinforcement Learning.
A8. Explain the steps required for selecting right machine learning algorithms.
A9. Construct classification tree using ID3 algorithm (Target attribute: Temperature)
Sr. No. Temp Wind Humidity
1 Hot Weak Normal
2 Hot Strong High
3 Mild Weak Normal
4 Mild Strong High
5 Cool Weak Normal
6 Mild Strong Normal
7 Mild Weak High
8 Hot Strong Normal
9 Mild Strong Normal
10 Cool Strong Normal

A10. Explain classification with Bayesian Belief Network with an example.

A11. Define SVM and further explain the maximum margin linear separator concept.
A12. Explain Reinforcement Learning in detail along with various elements involved in
forming the concept. Also define what is meant by partially observable state.
A13. Write short note on : Model based learning.
A14. Define well posed learning problem. Hence define robot driving learning problem.
A15. Explain in brief Bayesian belief network.
A16. Explain procedure to construct decision tree.
A17. Explain how SVM can be used to find optimal hyper plane to classify linearly seperable
data. Give example.
A18. Explain procedure to design machine learning system.
A19. What is linear regression find the best fifing line for
__
Sr. Xi Yi Yi
N
o
.
1 63 127 120.1
2 64 121 126.3
3 66 142 138.5
4 69 157 157.0
5 69 162 157.0
6 71 156 169.2
7 71 169 169.2
8 72 165 175.4
9 73 181 181.5
10 75 208 193.8

A20. What is decision tree? How you will choose best attribute for decision tree classifier?
Give suitable example.
A21. What is kernel? How kernel can be used with SVM to classify non-linearly separable
data? Also, list standard kernel functions.
A22. Explain following terms with respect to Reinforcement learning: delayed rewards,
exploration, and partially observable states.
A23. Write short notes on: (a) Soft margin SVM , (b) Radial Basis functions, (c) Independent
Component Analysis, (d) Logistic Regression.
A24. Explain the steps required for selecting right machine learning algorithm.
A25. Using Bayesian Classification and given data classify tuple (Rupesh, M, 1.73m)
 Count Probability
Attribute Value
Short Medium Tall Short Medium Tall
M 1 2 3 1/4 2/7 3/4
Gender
F 3 5 1 3/4 5/7 1/4
(0,1.6) 2 0 0 2/4 0 0
(1.6,1.7) 2 0 0 2/4 0 0
(1.7,1.8) 0 3 0 0 3/7 0
Height
(1.8,1.9) 0 3 0 0 3/7 0
(1.9,2) 0 1 2 0 1/7 2/4
(2,INFINITY) 0 0 2 0 0 2/4

A26. Write short note on quadratic programming solution for finding maximum margin
separator in SVM.
A27. What is machine learning? Explain how supervised learning is different from
unsupervised learning?
A28. Describe two methods for dimensionality reduction.
A29. The following table shows the midterm and the final exam grades obtained for students.
Use the method of least square regression to predict the final exam grades of a student
who received 86 marks in midterm exam.
Midterm End Exam
Mark Marks
s
72 84
50 83
81 77
74 78
94 90
86 75
59 49
83 79
 65 77
33 52
88 74
81 90

A30. The values of independent variable X and dependent variable Y are given below. Find
the least square regression line ax+b. Estimate the value of Y when X is 10.
X Y
0 2
1 3
2 5
3 4

4 6

A31. Write short note on : Issues in machine learning.

A32. Define Machine Learning (ML) Briefly explain the types of learning.
A33. “Entropy is a thermodynamic function used to measure the disorder of a system in
Chemistry.” How do you suitably clarify the concept of entropy in ML?
A34. State the principle of Occam’s Razar. Which ML algorithm uses this principle?
A35. Explain Bayesian Belief Network with an example.
A36. Compare and contrast Linear and Logistic regressions with respect to their mechanisms
of prediction.
A37. Find predicted value of Y for one epoch and RMSE using Linear regression.
X Y Actual
2 1
3 3
4 6
5 9
6 11
7 13
 8 15
9 17
10 20
A38. Write short note on feature engineering.
A39. Compute the structure of the decision tree using ID3 algorithm for following dataset.
Best
E
f
f
Match Courte o
Typ Sur r
Time e face t Outcome
Morning Master Grass 1 F
Afternoon GrandSlam Clay 1 F
Night Friendly Hard 0 F
Afternoon Friendly Mixed 0 N
Afternoon Master Clay 1 N
Afternoon GrandSlam Grass 1 F
Afternoon GrandSlam Hard 1 F
Afternoon GrandSlam Hard 1 F
Morning Master Grass 1 F
Afternoon GrandSlam Clay 1 N
Night Friendly Hard 0 F
Night Master Mixed 1 N
Afternoon Master Clay 1 N
Afternoon Master Grass 1 F
Afternoon GrandSlam Hard 1 F
Afternoon GrandSlam Clay 1 F

A40. Which of the following is true or false? Justify your answer.

 i. Root mean square error is a good performance measure for multi class classification
problem.
ii. Cross validation is expected to reduce the variance in the estimate of error rate of a
classifier.
iii. Training set error will initially decrease and then increase as we increase the parameter
C in soft margin SVM training.

A41. Consider the following balloon dataset. Compute the parameters of Naïve Bayes
Classifier for predicting inflated.
Colour Size Act Age Inflated
Yellow Small Stretch Adult T
Yellow Small Stretch Child T
Yellow Small Dip Adult T
Yellow Small Dip Child T
Yellow Large Stretch Adult T
Yellow Large Stretch Child F
Yellow Large Dip Adult F
Yellow Large Dip Child F
Purple Small Stretch Adult T
Purple Small Stretch Child F
Purple Small Dip Adult F
Purple Small Dip Child F
Purple Large Stretch Adult T
Purple Large Stretch Child F
Purple Large Dip Adult F
Purple Large Dip Child F

A42. Following dataset will be used to learn a decision tree for predicting whether the
mushrooms are edible or not.
Shape Color Odor Edible
 C B 1 y
D B 1 y
D W 1 y
D W 2 y
C B 2 y
D B 2 n
D G 2 n
C U 2 n
C B 3 n
C W 3 n
D W 3 n

What is the entropy H(Ediblel(Odor = 1 OR Odor = 3))? Which attribute would the ID3
algorithm choose to use for the root of the tree (no pruning)? Draw the full decision
tree that would be learned for this data (no pruning). Suppose we have the validation set
given in Table 3.
Shape Color Odor Edible
C B 2 N
D B 2 N
C W 2 Y

What will be the training set error and validation set error of the tree? Express your answer as
the number of examples that would be misclassified.
A43. Suppose you have the following training set with three boolean input x, y and z , and a
boolean output U.
X Y Z U
1 0 0 0
0 1 1 0
0 0 1 0
1 0 0 1
 0 0 1 1
0 1 0 1
1 1 0 1

Suppose you have to predict U using a Naive Bayes classifier. After learning is complete what
would be the predicted probability P(U = 0lx = 0, y = 1, Z = 0)?
Using the probabilities obtained during the Bayes Classifier training, what would be the
predicted probability P(U = 0lz = 0)?
In the next two parts, assume we learned a Joint Bayes Classifier. In that case what is P(U = 0lx
= 0, y = 1, Z = 0)?
What is P(U = 0lx = 0)?
A44. Define Machine learning? Briefly explain the types of learning.
A45. What is independent component analysis?
A46. What are the issues in decision tree induction?
A47. What are the requirements of clustering algorithms?
The values of independent variable x and dependent value y are given below:
X Y
0 2
1 3
2 5
3 4
4 6

Find the least square regression line y=ax+b. Estimate the value of y when x is 10.
A48. What are the steps in designing a machine learning problem? Explain the checkers
problem.
A49. For a SunBurn dataset given below, construct a decision tree
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
A50. What is the goal of the support vector machine (SVM)? How to compute the margin
A51. For the given set of points identify clusters using complete link and average link using
agglomerative clustering.
A A B
P1 1 1
P2 1.5 1.5
P3 5 5
P4 3 4
P5 4 4
P6 3 3.5
A52. What is the role of radial basis function in separating nonlinear patterns.
A53. Use Principle component analysis (PCA) to arrive at the transformed matrix for the
given matrix A.
A54. What are the elements of reinforcement learning?
A55. Write short notes on any two: Logistic regression, Back propogation algorithm, issues in
machine Learning
A56. Explain regression line, scatter plot, Error in prediction and best fitting line.
A57. Describe essential steps of K Mean algorithm for clustering analysis.
A58. Create a decision tree for the attribute ‘Class’
Eyecolour Married Sex Hairlenght class
Brown Yes Male Long football
Blue Yes Male Short football
Brown Yes Male Long football
Brown No Female Long Netball
 Brown No Female Long Netball
Blue No Male Long Football
Brown No Female Long Netball
Brown No Male Short Football
Brown Yes Female Short Netball
Brown No Female Long Netball
Blue No Male Long Football
Blue No Male Short Football
A59. Explain K-mean clustering algorithm giving suitable example. Also, explain how
Kmean clustering differs from hierarchical clustering.
A60. Describe essential steps of K Mean algorithm for clustering analysis.
A61. Apply K-Mean algorithm on given data for K = 3. Use C1(2), C2(16), and C3(38) as
initial cluster centers. Data: (2,4,6,3,31,13,15,16,38,35,14,21,23,25,30)
A62. Apply K-Mean algorithm on given data for K = 2. Use C1(2,4) and C2(6,3) as initial
cluster centers. Data: a(2,4), b(3,3), c(5,5), d(6,3), e(4,3), f(6,6)
A63. Apply agglomerative clustering algorithm and draw dendogram. Show three clusters
with its allocated points. Use single link method.
Adjacency Matrix:

A64. Write short note on hierarchical clustering algorithm.

A65. For the given set of points identify clusters using complete link and average link using
agglomerative clustering.
A66. Use the k-means clustering algorithm and Euclidean distance to cluster the following
eight examples into three clusters: A1= (2, 10), A2= (2, 5), A3= (8, 4), A4= (5, 8), A5=
(7, 5), A6= (6, 4), A7= 1(1, 2), A8= (4, 9). Find the new centroid at every new point
entry into the cluster group. Assume initial cluster centers as A1, A4 and A7.
A67. For the given set of points identify clusters using single linkage and draw the
dendrogram with cluster separation line emerging at 1.3. Find how many clusters are
formed below the line?

A B C D E F
A 0
B 0.71 0
C 5.66 4.95 0
D 3.61 2.92 2.24 0
E 4.24 3.54 1.41 1 0
F 3.20 2.50 2.50 0.50 1.12 0

A68. Write short note on density based clustering.

A69. Define the following terms
a. Sample error
b. True error
c. Random Variable
d. Expected value
e. Variance
f. standard Deviation
A70. Explain Binomial Distribution with an example. Explain Normal or Gaussian
distribution with an example.
A71. What is linearly in separable problem? Design a two layer network of perceptron to
implement A OR B

A72. Explain the following terms with reference to computational learning.

I. Training error.
II. True error
A73. With the help of block diagram explain the probably approximately correct (PAC)
learning model.
A74. What are the steps in Back propagation algorithm? Why a Multilayer neural
network is required?
A75. Describe these terms in brief (I) PAC Hypothesis (II) Mistake bound model of learning
A76. If you add more hidden layers to a feedforward neural network, can you always improve
performance on both your training and test sets? Explain.
A77. Write short note on back-propagation algorithm.
B1. Use the k-means clustering algorithm and Euclidean distance to cluster the following
eight examples into three clusters: A1= (2, 10), A2= (2, 5), A3= (8, 4), A4= (5, 8), A5=
(7, 5), A6= (6, 4), A7= 1(1, 2), A8= (4, 9). Find the new centroid at every new point
entry into the cluster group. Assume initial cluster centers as A1, A4 and A7.
B2. Compare and contrast Linear and Logistic regressions with respect to their mechanisms
of prediction.
B3. What is Temporal Difference Learning.
B4. What is the role of radial basis function in separating nonlinear patterns.
B5. Explain quadratic programming solution used to find maximum margin separation in
Support Vector Machine.
B6. What is Support Vector Machine? How to compute margins?
B7. Explain procedure to construct decision trees.
B8. Explain with suitable example advantage of Bayesian approach over classical approach
to probability.
B9. Write short note on issues in decision trees.

B10. Explain find –S algorithm with given example. Give its application.
Air
T
e
m
Example Sky p Humidity Wind Water ForeCast EnjoySports
1 Sunny Warm Normal Strong Warm Same Yes
2 Sunny Warm High Strong Warm Same Yes
3 Rain Cold High Strong Warm Change No
 4 Sunny Warm High Strong Cool Change Yes

B11. Use ID3 classifier to construct a decision tree for the following data set

B12. How is Candidate Elimination algorithm different from Find-S Algorithm?

B13. Differentiate between Training data and Testing Data
B14. Differentiate between Supervised, Unsupervised and Reinforcement Learning
B15. Explain the concept of Inductive Bias
B16. With a neat diagram, explain how you can model inductive systems by equivalent
deductive systems
B17. What do you mean by Concept Learning?
B18. Discuss the effect of reduced Error pruning in decision tree algorithm. What type of
problems are best suited for decision tree learning
B19. Define (a) Preference Bias (b) Restriction Bias
B20. Describe Reduced Error Pruning
B21. What are the alternative measures for selecting attributes? Explain with example.
B22. What is Rule Post Pruning?

B23. What are the important objectives of machine learning? What are the basic design issues
and approaches to machine learning?
Instance Classification a1 a2
1 + T T
2 + T T
3 - T F
4 + F F
5 - F T
6 - F T

B24. What is the entropy of this (above) collection of training example with respect to target
function classification? What is information gain of a2 relative to these training
examples?
B25. Describe K-nearest Neighbour learning Algorithm for continues valued target function.
B26. Discuss the major drawbacks of K-nearest Neighbour learning Algorithm and how it
can be corrected.
B27. Define the following terms
a. Sample error
b. True error
c. Random Variable
d. Expected value
e. Variance
f. standard Deviation
B28. Explain Binomial Distribution with an example. Explain Normal or Gaussian
distribution with an example.
B29. What is linearly in separable problem? Design a two layer network of perceptron to
implement A OR B
B30. Consider a multilayer feed forward neural network. Enumerate and explain steps
in back propagation algorithm use to train network.

B31. Explain how back propagation algorithm works for multilayer feed forward network.
B32. Explain the following terms with reference to computational learning.
Training error.
True error
B33. With the help of block diagram explain the probably approximately correct (PAC)
learning model.
B34. What are the steps in Back propagation algorithm? Why a Multilayer neural
network is required?
B35. Describe these terms in brief (I) PAC Hypothesis (II) Mistake bound model of learning
B36. If you add more hidden layers to a feedforward neural network, can you always improve
performance on both your training and test sets? Explain.
B37. For a fixed network architecture, is the backpropagation algorithm guaranteed to find
the best possible set of weights, given sufficient training data? Explain.
B38. Write short note on back-propagation algorithm.
B39. Explain classification using back propagation algorithm with suitable example.
B40. What is Artificial Neural Network?
B41. What are the type of problems in which Artificial Neural Network can be applied?
B42. Explain the concept of a Perceptron with a neat diagram.
B43. Discuss the Perceptron training rule.
B44. Under what conditions the perceptron rule fails and it becomes necessary to apply the
delta rule?
B45. What do you mean by Gradient Descent?
B46. Derive the Gradient Descent Rule.
B47. What are the conditions in which Gradient Descent is applied?
B48. What are the difficulties in applying Gradient Descent?
B49. Differentiate between Gradient Descent and Stochastic Gradient Descent
B50. Define Delta Rule.
B51. Derive the Backpropagation rule considering the training rule for Output Unit weights
and Training Rule for Hidden Unit weights
B52. Explain how to learn Multilayer Networks using Gradient Descent Algorithm.
B53. Explain working of sentimentr() function in R programming language along with it’s
algorithm / pseudo-code and code of the function.
B54. Explain working of naivebayes() function in R programming language along with it’s
algorithm / pseudo-code and code of the function.
B55. Explain working of knn() function in R programming language along with it’s algorithm
/ pseudo-code and code of the function.
B56. Explain working of C5.0() function in R programming language along with it’s
algorithm / pseudo-code and code of the function.
B57. Explain working of lm() function in R programming language along with it’s algorithm
/ pseudo-code and code of the function.
B58. Explain working of glm() function in R programming language along with it’s
algorithm / pseudo-code and code of the function.
B59. Explain working of svm() function in R programming language along with it’s
algorithm / pseudo-code and code of the function.
B60. What is linear regression? Write and explain mathematical model behind it. Write its
applications, advantages and disadvantages. Explain with example. Write python and R
code to implement linear regressor for an exemplary dataset.
B61. What is logistic regression? Write and explain mathematical model behind it. Write its
applications, advantages and disadvantages. Explain with example. Write python and R
code to implement logistic regressor for an exemplary dataset.
B62. What is decision tree? How to construct it? Write and explain mathematical model
behind it. Explain with a suitable example. . Write python and R code to implement it
for an exemplary dataset.
B63. What is instance based learning? Write and explain mathematical model behind it.
Write its applications, advantages and disadvantages. Write and explain pseudo code for
KNN classifier. Write python and R code to implement it for an exemplary dataset.
B64. Explain the working of Naïve Bayes Classifier along with its applications, advantages
and disadvantages. Write and explain mathematical model behind it. Write and explain
pseudo code for it. Write python and R code to implement it for an exemplary dataset.
B65. Explain the working of SVM Classifier along with its applications, advantages and
disadvantages. Write and explain mathematical model behind it. Write python and R
code to implement it for an exemplary dataset.
B66. Define Machine learning? Briefly explain the types of learning.
B67. What is independent component analysis?
B68. What are the issues in decision tree induction?
B69. What are the requirements of clustering algorithms?
B70. The values of independent variable x and dependent value y are given below:
 B71. X B72. Y
B73. 0 B74. 2
B75. 1 B76. 3
B77. 2 B78. 5
B79. 3 B80. 4
B81. 4 B82. 6
Find the least square regression line y=ax+b. Estimate the value of y when x is 10.
B71.What are the steps in designing a machine learning problem? Explain the checkers
problem.
B72. For a SunBurn dataset given below, construct a decision tree
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
B73. What is the goal of the support vector machine (SVM)? How to compute the margin
B 74. For the given set of points identify clusters using complete link and average link using
agglomerative clustering.
A A B
P1 1 1
P2 1.5 1.5
P3 5 5
P4 3 4
P5 4 4
P6 3 3.5
B75. What is the role of radial basis function in separating nonlinear patterns.
B 76. Use Principle component analysis (PCA) to arrive at the transformed matrix for the given
matrix A.