Download Visvesvaraya Technological University (VTU) BE ( Bachelor of Engineering) CSE 2015 Scheme 2020 January Previous Question Paper 7th Sem 15CS73 Machine Learning
..
v
.
;1
,, r-
CHIkiDOI
f /
15CS73
..,..c cN
c
)
N
Seventh Semester B.E. Degree Examination, Dec
e'N
"An.2020
Machine Learning
7
USN
Time: 3 hrs. Max. Marks: 80
Note: Answer any FIVE full questions, choosing ONE full question from each module.
Module-1
1 a. What do you mean by well-posed learning problem? Explain with example. (04 Marks)
b. Explain the various stages involved in designing a learning system in brief. (08 Marks)
c. Write Find S algorithm and discuss the issues with the algorithm. (04 Marks)
OR
2 a. List the issues in machine learning. (04 Marks)
b. Consider the given below training example which finds malignant tumors from MRI scans.
Example Shape Size Color Surface Thickness Target concept
1 Circular Large Light Smooth Thick Malignant
2 Circular Large Light Irregular Thick Malignant
3 Oval Large Dark Smooth Thin Benign
4 Oval Large Light Irregular Thick Malignant
5 Circular Small Light Smooth Thick Benign
Show the specific and general boundaries of the version space after applying candidate
elimination algorithm. (Note: Malignant is +ve, Benign is ?ye). (08 Marks)
c. Explain the concept of inductive bias in brief. (04 Marks)
Module-2
3 a. Discuss the two approaches to prevent over fitting the data.
b. Consider the following set of training examples:
Instance Classification al a2
I 1 1 1
2 1 1 1
3 0 1 0
4 I 0 0
5 0 0 1
6 0 0 1
(08 Marks)
(i) What is the entropy of this collection of training examples with respect to the target
function classification?
(ii) What is the information gain of a2 relative to these training examples? (08 Marks)
OR
4 a. Define decision tree. Construct the decision tree to represent the following Boolean
functions:
i) A A?B ii) A v [B n C] iii) A XOR B (06 Marks)
b. Write the ID3 algorithm. (06 Marks)
c. What do you mean by gain and entropy? How it is used to build the decision tree. (04 Marks)
1 of 2
FirstRanker.com - FirstRanker's Choice
./
..
v
.
;1
,, r-
CHIkiDOI
f /
15CS73
..,..c cN
c
)
N
Seventh Semester B.E. Degree Examination, Dec
e'N
"An.2020
Machine Learning
7
USN
Time: 3 hrs. Max. Marks: 80
Note: Answer any FIVE full questions, choosing ONE full question from each module.
Module-1
1 a. What do you mean by well-posed learning problem? Explain with example. (04 Marks)
b. Explain the various stages involved in designing a learning system in brief. (08 Marks)
c. Write Find S algorithm and discuss the issues with the algorithm. (04 Marks)
OR
2 a. List the issues in machine learning. (04 Marks)
b. Consider the given below training example which finds malignant tumors from MRI scans.
Example Shape Size Color Surface Thickness Target concept
1 Circular Large Light Smooth Thick Malignant
2 Circular Large Light Irregular Thick Malignant
3 Oval Large Dark Smooth Thin Benign
4 Oval Large Light Irregular Thick Malignant
5 Circular Small Light Smooth Thick Benign
Show the specific and general boundaries of the version space after applying candidate
elimination algorithm. (Note: Malignant is +ve, Benign is ?ye). (08 Marks)
c. Explain the concept of inductive bias in brief. (04 Marks)
Module-2
3 a. Discuss the two approaches to prevent over fitting the data.
b. Consider the following set of training examples:
Instance Classification al a2
I 1 1 1
2 1 1 1
3 0 1 0
4 I 0 0
5 0 0 1
6 0 0 1
(08 Marks)
(i) What is the entropy of this collection of training examples with respect to the target
function classification?
(ii) What is the information gain of a2 relative to these training examples? (08 Marks)
OR
4 a. Define decision tree. Construct the decision tree to represent the following Boolean
functions:
i) A A?B ii) A v [B n C] iii) A XOR B (06 Marks)
b. Write the ID3 algorithm. (06 Marks)
c. What do you mean by gain and entropy? How it is used to build the decision tree. (04 Marks)
1 of 2
Module-3
5 a. Define perceptron. Explain the concept of single perceptron with neat diagram. (06 Marks)
b. Explain the back propagation algorithm. Why is it not likely to be trapped in local minima?
(10 Marks)
OR
6 a. List the appropriate problems for neural network learning.
b. Discuss the perceptron training rule and delta rule that solves the learning
perceptron.
c. Write a remark on representation of feed forward networks.
Module-4
7 a. Explain Na?ve Bayes classifier.
b. Explain brute force MAP learning algorithm.
OR
8 a. Discuss Minimum Description Length principle in brief.
b. Explain Bayesian belief networks and conditional independence with example.
Module-5
9 a. Define: (i) Simple Error (ii) True Error
b. Explain K-nearest neighbor learning algorithm.
c. What is reinforcement learning?
(04 Marks)
problem of
(08 Marks)
(04 Marks)
(08 Marks)
(08 Marks)
(08 Marks)
(08 Marks)
(04 Marks)
(08 Marks)
(04 Marks)
OR
10 a. Define expected value, variance, standard deviation and estimate bias of a random variable.
(04 Marks)
Explain locally weighted linear regression. (08 Marks)
Write a note on Q-learning. (04 Marks)
*
,/
" ?
;
-F
s
it
/ :1,- ; ?
b.
c.
2 of 2
FirstRanker.com - FirstRanker's Choice
This post was last modified on 02 March 2020